Upload folder using huggingface_hub

.gitattributes

@@ -177,3 +177,10 @@ sft/1M3/std_0.002_Full_smoe/checkpoint-27572/trainer_state.json filter=lfs diff=
 sft/1M3/std_0.002_Full_smoe/checkpoint-34462/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 sft/1M3/std_0.002_Full_smoe/checkpoint-20679/trainer_state.json filter=lfs diff=lfs merge=lfs -text
 sft/1M3/Full_remoe/checkpoint-13786/trainer_state.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/pope.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/infovqa_val.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_remoe/logs/0626_1526_llava_v1.5_gqa_llava_model_args_5c6951/gqa.json filter=lfs diff=lfs merge=lfs -text

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/mmbench_en_dev.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e338d074e23e1872cddf1c3265f03335be0392eb8be0887b57239861bb427f
+size 14568172

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/mmerealworld_lite.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5c161d4829e2d2a8153ac2476056de425f290323213bd691fd720447d34291
+size 1994104219

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/pope.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a102e9d8f0408982a190bb416b7412f87d6753a07de398c912fe57f79d72a26a
+size 17631894

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/rank0_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 0 eval done

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/rank1_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 1 eval done

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/rank2_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 2 eval done

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/rank3_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 3 eval done

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/results.json

@@ -0,0 +1,488 @@
+{
+    "results": {
+        "ai2d": {
+            "exact_match,flexible-extract": 0.6386010362694301,
+            "exact_match_stderr,flexible-extract": 0.008646492043965488,
+            "alias": "ai2d"
+        },
+        "mmbench_en_dev": {
+            "gpt_eval_score,none": 56.87285223367697,
+            "gpt_eval_score_stderr,none": "N/A",
+            "submission,none": null,
+            "submission_stderr,none": "N/A",
+            "alias": "mmbench_en_dev"
+        },
+        "mmerealworld_lite": {
+            "mme_realworld_score,none": 0.266284523189161,
+            "mme_realworld_score_stderr,none": "N/A",
+            "alias": "mmerealworld_lite"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.40778,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.527471270436267,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.25409604519774015,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.4326050159685535,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.32938293829382936,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.3639902432504678,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.22466506472791004,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        },
+        "pope": {
+            "pope_accuracy,none": 0.11666666666666667,
+            "pope_accuracy_stderr,none": "N/A",
+            "pope_precision,none": 0.7718808193668529,
+            "pope_precision_stderr,none": "N/A",
+            "pope_recall,none": 0.9200887902330743,
+            "pope_recall_stderr,none": "N/A",
+            "pope_f1_score,none": 0.839493670886076,
+            "pope_f1_score_stderr,none": "N/A",
+            "pope_yes_ratio,none": 0.5,
+            "pope_yes_ratio_stderr,none": "N/A",
+            "alias": "pope"
+        },
+        "textvqa_val": {
+            "exact_match,none": 0.228200000166893,
+            "exact_match_stderr,none": 0.005759964181277439,
+            "submission,none": null,
+            "submission_stderr,none": "N/A",
+            "alias": "textvqa_val"
+        }
+    },
+    "configs": {
+        "ai2d": {
+            "task": "ai2d",
+            "dataset_path": "lmms-lab/ai2d",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function ai2d_doc_to_visual at 0x7fd1204d2670>",
+            "doc_to_text": "<function ai2d_doc_to_text at 0x7fd1204d2940>",
+            "doc_to_target": "<function ai2d_doc_to_target at 0x7fd1204d2ee0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "exact_match",
+                    "aggregation": "mean",
+                    "higher_is_better": true,
+                    "ignore_case": true,
+                    "ignore_punctuation": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 512,
+                "temperature": 0.0,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "filter_list": [
+                {
+                    "name": "flexible-extract",
+                    "filter": [
+                        {
+                            "function": "<class 'utils.MultiChoiceRegexFilter'>",
+                            "group_select": 0,
+                            "ignore_case": true,
+                            "ignore_punctuation": true,
+                            "regex_pattern": "([A-Z])\\."
+                        }
+                    ]
+                }
+            ],
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "prompt_format": "mcq",
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer with the option's letter from the given choices directly."
+                },
+                "gpt4v": {
+                    "prompt_format": "mcq",
+                    "pre_prompt": "",
+                    "post_prompt": "\nAbove choices are given in {option}. {content} format.\nPlease answer with the option letter from the given choices directly."
+                },
+                "qwen_vl": {
+                    "prompt_format": "qa",
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                },
+                "xcomposer2_4khd": {
+                    "prompt_format": "mcq_xcomposer",
+                    "pre_prompt": "[UNUSED_TOKEN_146]user\nQuestion: ",
+                    "post_prompt": "[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\nThe answer is"
+                }
+            },
+            "model_specific_target_kwargs": {
+                "default": "mcq",
+                "qwen_vl": "qa"
+            }
+        },
+        "mmbench_en_dev": {
+            "task": "mmbench_en_dev",
+            "dataset_path": "lmms-lab/MMBench",
+            "dataset_name": "en",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "dev",
+            "doc_to_visual": "<function mmbench_doc_to_visual at 0x7fd18005aee0>",
+            "doc_to_text": "<function mmbench_doc_to_text at 0x7fd180066430>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmbench_process_results at 0x7fd180066940>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mmbench_aggregate_dev_results_eval at 0x7fd18005a790>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "submission",
+                    "aggregation": "<function mmbench_aggregate_dev_results_submission at 0x7fd18005aca0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "until": [
+                    "ASSISTANT:"
+                ],
+                "max_new_tokens": 1024,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "image_aspect_ratio": "original"
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer with the option's letter from the given choices directly."
+                }
+            },
+            "model_specific_generation_kwargs": {
+                "llava": {
+                    "image_aspect_ratio": "original"
+                }
+            }
+        },
+        "mmerealworld_lite": {
+            "task": "mmerealworld_lite",
+            "dataset_path": "yifanzhang114/MME-RealWorld-lite-lmms-eval",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "train",
+            "doc_to_visual": "<function mme_realworld_doc_to_visual at 0x7fd120c7b820>",
+            "doc_to_text": "<function mme_realworld_doc_to_text at 0x7fd120c80310>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_realworld_process_results at 0x7fd120c80f70>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_realworld_score",
+                    "aggregation": "<function mme_realworld_aggregate_results at 0x7fd120c84af0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nSelect the best answer to the above multiple-choice question based on the image. Respond with only the letter (A, B, C, D, or E) of the correct option."
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nSelect the best answer to the above multiple-choice question based on the image. Respond with only the letter (A, B, C, D, or E) of the correct option."
+                },
+                "xcomposer2_4khd": {
+                    "pre_prompt": "[UNUSED_TOKEN_146]user\n",
+                    "post_prompt": " Answer this question with A, B, C, or D.[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\n"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7fd133c7d280>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7fd133c7df70>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7fd133aeae50>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7fd133abddc0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 128,
+                "until": [
+                    "\n\n"
+                ],
+                "image_aspect_ratio": "original"
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_generation_kwargs": {
+                "llava": {
+                    "image_aspect_ratio": "original"
+                }
+            }
+        },
+        "mmstar": {
+            "task": "mmstar",
+            "dataset_path": "Lin-Chen/MMStar",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "val",
+            "doc_to_visual": "<function mmstar_doc_to_visual at 0x7fd12042dca0>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7fd120432160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7fd120432670>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120432af0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120432ee0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120437310>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120437700>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120437af0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7fd120437ee0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "until": [
+                    "\n\n"
+                ],
+                "do_sample": false
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer with the option's letter from the given choices directly"
+                }
+            }
+        },
+        "pope": {
+            "task": "pope",
+            "dataset_path": "lmms-lab/POPE",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function pope_doc_to_visual at 0x7fd120d14310>",
+            "doc_to_text": "<function pope_doc_to_text at 0x7fd120d148b0>",
+            "doc_to_target": "answer",
+            "process_results": "<function pope_process_results at 0x7fd120d14e50>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "pope_accuracy",
+                    "aggregation": "<function pope_aggregate_accuracy at 0x7fd120d17430>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "pope_precision",
+                    "aggregation": "<function pope_aggregate_precision at 0x7fd120d179d0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "pope_recall",
+                    "aggregation": "<function pope_aggregate_recall at 0x7fd120d17f70>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "pope_f1_score",
+                    "aggregation": "<function pope_aggregate_f1_score at 0x7fd120d1e550>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "pope_yes_ratio",
+                    "aggregation": "<function pope_aggregate_yes_ratio at 0x7fd120d1eaf0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 128,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ]
+        },
+        "textvqa_val": {
+            "task": "textvqa_val",
+            "dataset_path": "lmms-lab/textvqa",
+            "test_split": "validation",
+            "doc_to_visual": "<function textvqa_doc_to_visual at 0x7fd14dfb2310>",
+            "doc_to_text": "<function textvqa_doc_to_text at 0x7fd14dfb2790>",
+            "doc_to_target": "answer",
+            "process_results": "<function textvqa_process_results at 0x7fd14dfb2a60>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "exact_match",
+                    "aggregation": "mean",
+                    "higher_is_better": true,
+                    "ignore_case": true,
+                    "ignore_punctuation": true
+                },
+                {
+                    "metric": "submission",
+                    "aggregation": "<function textvqa_aggregate_submissions at 0x7fd14dfb20d0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "until": [
+                    "ASSISTANT:"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question using a single word or phrase.",
+                    "ocr": false
+                },
+                "qwen_vl": {
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                }
+            }
+        }
+    },
+    "versions": {
+        "ai2d": "Yaml",
+        "mmbench_en_dev": "Yaml",
+        "mmerealworld_lite": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml",
+        "pope": "Yaml",
+        "textvqa_val": "Yaml"
+    },
+    "n-shot": {
+        "ai2d": 0,
+        "mmbench_en_dev": 0,
+        "mmerealworld_lite": 0,
+        "mmmu_val": 0,
+        "mmstar": 0,
+        "pope": 0,
+        "textvqa_val": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78/checkpoints/Xphi35-siglip224/SMOE/1M3/Full_remoe,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/submissions/mmbench_en_dev_results.json

@@ -0,0 +1 @@
+{"overall_acc": 0.5687285223367697, "category_acc": {"action_recognition": 0.8333333333333334, "attribute_comparison": 0.5681818181818182, "attribute_recognition": 0.6621621621621622, "celebrity_recognition": 0.5050505050505051, "function_reasoning": 0.7848101265822784, "future_prediction": 0.45, "identity_reasoning": 0.9111111111111111, "image_emotion": 0.6, "image_quality": 0.11320754716981132, "image_scene": 0.8653846153846154, "image_style": 0.5471698113207547, "image_topic": 0.8333333333333334, "nature_relation": 0.4583333333333333, "object_localization": 0.2962962962962963, "ocr": 0.6666666666666666, "physical_property_reasoning": 0.4666666666666667, "physical_relation": 0.5833333333333334, "social_relation": 0.6046511627906976, "spatial_relationship": 0.2, "structuralized_imagetext_understanding": 0.3974358974358974}, "l2_category_acc": {"attribute_reasoning": 0.6934673366834171, "coarse_perception": 0.625, "finegrained_perception (cross-instance)": 0.5524475524475524, "finegrained_perception (instance-level)": 0.5085324232081911, "logic_reasoning": 0.4152542372881356, "relation_reasoning": 0.5391304347826087}}

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/submissions/mmbench_en_dev_results.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e3987dd40b3c51303a503803c88d21648f4b4e77f5160b192a87710d38a5c7
+size 865158

sft/1M3/Full_remoe/logs/0620_0432_llava..._pope_llava_model_args_5c6951/textvqa_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b194e6d65a8f957801b07c572dd505e0a4edb0a4c6d3d18c49c4f89a3fbfcb7a
+size 13193476

sft/1M3/Full_remoe/logs/0626_1501_llava...l_mme_llava_model_args_5c6951/rank0_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 0 eval done

sft/1M3/Full_remoe/logs/0626_1501_llava...l_mme_llava_model_args_5c6951/rank1_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 1 eval done

sft/1M3/Full_remoe/logs/0626_1501_llava...l_mme_llava_model_args_5c6951/rank2_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 2 eval done

sft/1M3/Full_remoe/logs/0626_1501_llava...l_mme_llava_model_args_5c6951/rank3_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 3 eval done

sft/1M3/Full_remoe/logs/0626_1501_llava...l_mme_llava_model_args_5c6951/results.json

@@ -0,0 +1,215 @@
+{
+    "results": {
+        "docvqa_val": {
+            "anls,none": 0.15797345298186577,
+            "anls_stderr,none": 0.0049872282869667045,
+            "alias": "docvqa_val"
+        },
+        "mme": {
+            "mme_cognition_score,none": 320.3571428571429,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1144.748799519808,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "scienceqa_img": {
+            "exact_match,none": 0.7530986613782846,
+            "exact_match_stderr,none": 0.009603784276255882,
+            "alias": "scienceqa_img"
+        }
+    },
+    "configs": {
+        "docvqa_val": {
+            "task": "docvqa_val",
+            "dataset_path": "lmms-lab/DocVQA",
+            "dataset_name": "DocVQA",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "validation",
+            "doc_to_visual": "<function docvqa_doc_to_visual at 0x7f6dbe75e4c0>",
+            "doc_to_text": "<function docvqa_doc_to_text at 0x7f6dbe75e820>",
+            "doc_to_target": "answers",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "anls",
+                    "aggregation": "mean",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 32,
+                "temperature": 0.0,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question using a single word or phrase."
+                },
+                "qwen_vl": {
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f6deacd48b0>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f6de9276160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f6de9276700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f6de9276c10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f6de927f0d0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question using a single word or phrase."
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question with Yes or No."
+                },
+                "qwen_vl": {
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                },
+                "otterhd": {
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                },
+                "xcomposer2_4khd": {
+                    "pre_prompt": "[UNUSED_TOKEN_146]user\n",
+                    "post_prompt": " Answer this question briefly[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\n"
+                }
+            }
+        },
+        "scienceqa_img": {
+            "task": "scienceqa_img",
+            "dataset_path": "lmms-lab/ScienceQA",
+            "dataset_name": "ScienceQA-IMG",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function sqa_doc_to_visual at 0x7f6db4e6fc10>",
+            "doc_to_text": "<function sqa_doc_to_text at 0x7f6db4e6fe50>",
+            "doc_to_target": "<function sqa_doc_to_target at 0x7f6db4df8280>",
+            "process_results": "<function sqa_process_results at 0x7f6db4df85e0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "exact_match",
+                    "aggregation": "mean",
+                    "higher_is_better": true,
+                    "ignore_case": true,
+                    "ignore_punctuation": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ],
+                "image_aspect_ratio": "original"
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "format": "default",
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer with the option's letter from the given choices directly."
+                },
+                "qwen_vl": {
+                    "format": "qwen_vl"
+                },
+                "idefics2": {
+                    "format": "default",
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer:"
+                }
+            },
+            "model_specific_generation_kwargs": {
+                "llava": {
+                    "image_aspect_ratio": "original"
+                }
+            }
+        }
+    },
+    "versions": {
+        "docvqa_val": "Yaml",
+        "mme": "Yaml",
+        "scienceqa_img": "Yaml"
+    },
+    "n-shot": {
+        "docvqa_val": 0,
+        "mme": 0,
+        "scienceqa_img": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78/checkpoints/Xphi35-siglip224/SMOE/1M3/Full_remoe,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/1M3/Full_remoe/logs/0626_1503_llava...image_llava_model_args_5c6951/rank0_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 0 eval done

sft/1M3/Full_remoe/logs/0626_1503_llava...image_llava_model_args_5c6951/rank1_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 1 eval done

sft/1M3/Full_remoe/logs/0626_1503_llava...image_llava_model_args_5c6951/rank2_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 2 eval done

sft/1M3/Full_remoe/logs/0626_1503_llava...image_llava_model_args_5c6951/rank3_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 3 eval done

sft/1M3/Full_remoe/logs/0626_1503_llava...image_llava_model_args_5c6951/results.json

@@ -0,0 +1,146 @@
+{
+    "results": {
+        "hallusion_bench_image": {
+            "aAcc,none": 44.4795,
+            "aAcc_stderr,none": "N/A",
+            "fAcc,none": 16.763,
+            "fAcc_stderr,none": "N/A",
+            "qAcc,none": 11.4286,
+            "qAcc_stderr,none": "N/A",
+            "alias": "hallusion_bench_image"
+        },
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 34.2,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        }
+    },
+    "configs": {
+        "hallusion_bench_image": {
+            "task": "hallusion_bench_image",
+            "dataset_path": "lmms-lab/HallusionBench",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "image",
+            "doc_to_visual": "<function hb_doc_to_visual at 0x7fc7f69f60d0>",
+            "doc_to_text": "<function hb_doc_to_text at 0x7fc7f69f6820>",
+            "doc_to_target": "gt_answer_details",
+            "process_results": "<function hb_process_results at 0x7fc7f694c040>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "aAcc",
+                    "aggregation": "<function hb_aggregation_result_aAcc at 0x7fc7f694c9d0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "qAcc",
+                    "aggregation": "<function hb_aggregation_result_qAcc at 0x7fc7f68cd040>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fAcc",
+                    "aggregation": "<function hb_aggregation_result_fAcc at 0x7fc7f68cd820>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 128,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": ""
+                }
+            }
+        },
+        "mathvista_testmini": {
+            "task": "mathvista_testmini",
+            "dataset_path": "AI4Math/MathVista",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "testmini",
+            "doc_to_visual": "<function mathvista_doc_to_visual at 0x7fc7cc111af0>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7fc7cbd091f0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7fc7cbd128b0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7fc7cbd1cf70>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "until": [
+                    "ASSISTANT:"
+                ],
+                "max_new_tokens": 1024,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "image_aspect_ratio": "original"
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "shot_type": "format-prompt",
+                    "shot": 0,
+                    "use_caption": false,
+                    "use_ocr": false
+                },
+                "phi3v": {
+                    "shot_type": "solution"
+                }
+            },
+            "model_specific_generation_kwargs": {
+                "llava": {
+                    "image_aspect_ratio": "original"
+                }
+            }
+        }
+    },
+    "versions": {
+        "hallusion_bench_image": "Yaml",
+        "mathvista_testmini": "Yaml"
+    },
+    "n-shot": {
+        "hallusion_bench_image": 0,
+        "mathvista_testmini": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78/checkpoints/Xphi35-siglip224/SMOE/1M3/Full_remoe,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/infovqa_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c524c34a69abfc7e6053cd85992721dd5f12b2a266568ed40349392bcf4ff75e
+size 576442330

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/rank0_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 0 eval done

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/rank1_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 1 eval done

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/rank2_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 2 eval done

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/rank3_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 3 eval done

sft/1M3/Full_remoe/logs/0626_1513_llava...a_val_llava_model_args_5c6951/results.json

@@ -0,0 +1,245 @@
+{
+    "results": {
+        "infovqa_val": {
+            "anls,none": 0.2784719742948947,
+            "anls_stderr,none": 0.00847107123069025,
+            "alias": "infovqa_val"
+        },
+        "mmmu_pro": {
+            "mmmu_acc,none": 0.18988499999999997,
+            "mmmu_acc_stderr,none": 0.033387325106623435,
+            "alias": "mmmu_pro"
+        },
+        "mmmu_pro_standard": {
+            "mmmu_acc,none": 0.25665,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": " - mmmu_pro_standard"
+        },
+        "mmmu_pro_vision": {
+            "mmmu_acc,none": 0.12312,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": " - mmmu_pro_vision"
+        },
+        "realworldqa": {
+            "exact_match,flexible-extract": 0.4392156862745098,
+            "exact_match_stderr,flexible-extract": 0.017955196829891946,
+            "alias": "realworldqa"
+        }
+    },
+    "groups": {
+        "mmmu_pro": {
+            "mmmu_acc,none": 0.18988499999999997,
+            "mmmu_acc_stderr,none": 0.033387325106623435,
+            "alias": "mmmu_pro"
+        }
+    },
+    "configs": {
+        "infovqa_val": {
+            "task": "infovqa_val",
+            "dataset_path": "lmms-lab/DocVQA",
+            "dataset_name": "InfographicVQA",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "validation",
+            "doc_to_visual": "<function infovqa_doc_to_visual at 0x7f852e796a60>",
+            "doc_to_text": "<function infovqa_doc_to_text at 0x7f852e796d30>",
+            "doc_to_target": "answers",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "anls",
+                    "aggregation": "mean",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 32,
+                "temperature": 0.0,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question using a single word or phrase."
+                }
+            }
+        },
+        "mmmu_pro_standard": {
+            "task": "mmmu_pro_standard",
+            "dataset_path": "MMMU/MMMU_Pro",
+            "dataset_name": "standard (10 options)",
+            "test_split": "test",
+            "doc_to_visual": "<function mmmu_pro_doc_to_visual at 0x7f8556d58790>",
+            "doc_to_text": "<function mmmu_pro_doc_to_text at 0x7f8556d62550>",
+            "doc_to_target": "{{answer}}",
+            "process_results": "<function mmmu_pro_process_results at 0x7f8556d6c4c0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_pro_aggregate_results at 0x7f8556d76430>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 256,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": {
+                "version": 0.0,
+                "interleaved_format": false
+            },
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "Answer with the option letter from the given choices directly."
+                }
+            }
+        },
+        "mmmu_pro_vision": {
+            "task": "mmmu_pro_vision",
+            "dataset_path": "MMMU/MMMU_Pro",
+            "dataset_name": "vision",
+            "test_split": "test",
+            "doc_to_visual": "<function mmmu_pro_doc_to_visual at 0x7f8556d44ca0>",
+            "doc_to_text": "Answer with the option letter from the given choices directly.",
+            "doc_to_target": "{{answer}}",
+            "process_results": "<function mmmu_pro_process_results at 0x7f8556d4db80>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_pro_aggregate_results at 0x7f8556d54af0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 256,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": {
+                "version": 0.0,
+                "interleaved_format": false
+            }
+        },
+        "realworldqa": {
+            "task": "realworldqa",
+            "dataset_path": "lmms-lab/RealWorldQA",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function realworldqa_doc_to_visual at 0x7f8526d32af0>",
+            "doc_to_text": "<function realworldqa_doc_to_text at 0x7f8526c43160>",
+            "doc_to_target": "answer",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "exact_match",
+                    "aggregation": "mean",
+                    "higher_is_better": true,
+                    "ignore_case": true,
+                    "ignore_punctuation": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "top_p": 1.0,
+                "num_beams": 1,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "filter_list": [
+                {
+                    "name": "flexible-extract",
+                    "filter": [
+                        {
+                            "function": "<class 'utils.NumberWordsToDigitsFilter'>"
+                        },
+                        {
+                            "function": "<class 'utils.MultiChoiceRegexFilter'>",
+                            "group_select": 0,
+                            "ignore_case": true,
+                            "ignore_punctuation": true,
+                            "regex_pattern": "(\\([A-Z]\\))"
+                        }
+                    ]
+                }
+            ],
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": ""
+                },
+                "gpt4v": {
+                    "pre_prompt": "",
+                    "post_prompt": ""
+                },
+                "xcomposer2_4khd": {
+                    "pre_prompt": "[UNUSED_TOKEN_146]user\nQuestion: ",
+                    "post_prompt": "[UNUSED_TOKEN_145]\n[UNUSED_TOKEN_146]assistant\nThe answer is"
+                }
+            }
+        }
+    },
+    "versions": {
+        "infovqa_val": "Yaml",
+        "mmmu_pro": "N/A",
+        "mmmu_pro_standard": "Yaml",
+        "mmmu_pro_vision": "Yaml",
+        "realworldqa": "Yaml"
+    },
+    "n-shot": {
+        "infovqa_val": 0,
+        "mmmu_pro": 0,
+        "mmmu_pro_standard": 0,
+        "mmmu_pro_vision": 0,
+        "realworldqa": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78/checkpoints/Xphi35-siglip224/SMOE/1M3/Full_remoe,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/1M3/Full_remoe/logs/0626_1520_llava..._plus_llava_model_args_5c6951/rank0_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 0 eval done

sft/1M3/Full_remoe/logs/0626_1520_llava..._plus_llava_model_args_5c6951/rank1_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 1 eval done

sft/1M3/Full_remoe/logs/0626_1520_llava..._plus_llava_model_args_5c6951/rank2_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 2 eval done

sft/1M3/Full_remoe/logs/0626_1520_llava..._plus_llava_model_args_5c6951/rank3_metric_eval_done.txt

@@ -0,0 +1 @@
+rank 3 eval done

sft/1M3/Full_remoe/logs/0626_1520_llava..._plus_llava_model_args_5c6951/results.json

@@ -0,0 +1,168 @@
+{
+    "results": {
+        "chartqa": {
+            "relaxed_overall,none": 0.124,
+            "relaxed_overall_stderr,none": 0.006592949779478021,
+            "relaxed_human_split,none": 0.1296,
+            "relaxed_human_split_stderr,none": 0.009503437497001176,
+            "relaxed_augmented_split,none": 0.1184,
+            "relaxed_augmented_split_stderr,none": 0.009141772782545212,
+            "alias": "chartqa"
+        },
+        "seedbench_2_plus": {
+            "seedbench_2_plus_Chart,none": 0.4728395061728395,
+            "seedbench_2_plus_Chart_stderr,none": "N/A",
+            "seedbench_2_plus_all,none": 0.48177426438296006,
+            "seedbench_2_plus_all_stderr,none": "N/A",
+            "seedbench_2_plus_Web,none": 0.5272727272727272,
+            "seedbench_2_plus_Web_stderr,none": "N/A",
+            "seedbench_2_plus_Map,none": 0.45353159851301117,
+            "seedbench_2_plus_Map_stderr,none": "N/A",
+            "alias": "seedbench_2_plus"
+        }
+    },
+    "configs": {
+        "chartqa": {
+            "task": "chartqa",
+            "dataset_path": "lmms-lab/ChartQA",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function chartqa_doc_to_visual at 0x7f538db64d30>",
+            "doc_to_text": "<function chartqa_doc_to_text at 0x7f538db6d790>",
+            "doc_to_target": "answer",
+            "process_results": "<function chartqa_process_results at 0x7f538db6da60>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "relaxed_overall",
+                    "aggregation": "mean",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "relaxed_human_split",
+                    "aggregation": "mean",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "relaxed_augmented_split",
+                    "aggregation": "mean",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "max_new_tokens": 16,
+                "temperature": 0.0,
+                "do_sample": false,
+                "until": [
+                    "\n\n"
+                ]
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "default": {
+                    "pre_prompt": "",
+                    "post_prompt": "\nAnswer the question with a single word."
+                },
+                "qwen_vl": {
+                    "pre_prompt": "",
+                    "post_prompt": " Answer:"
+                }
+            }
+        },
+        "seedbench_2_plus": {
+            "task": "seedbench_2_plus",
+            "dataset_path": "doolayer/SEED-Bench-2-Plus",
+            "dataset_kwargs": {
+                "token": true
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function seed_doc_to_visual at 0x7f53b6357ca0>",
+            "doc_to_text": "<function seed_doc_to_text at 0x7f53b637e310>",
+            "doc_to_target": "answer",
+            "process_results": "<function seed_process_result at 0x7f53b637e820>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "seedbench_2_plus_Chart",
+                    "aggregation": "<function seed_aggregation_result at 0x7f53b637ed30>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "seedbench_2_plus_Map",
+                    "aggregation": "<function seed_aggregation_result at 0x7f53b61231f0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "seedbench_2_plus_Web",
+                    "aggregation": "<function seed_aggregation_result at 0x7f53b6123670>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "seedbench_2_plus_all",
+                    "aggregation": "<function seed_aggregation_result at 0x7f53b6123af0>",
+                    "higher_is_better": true
+                }
+            ],
+            "output_type": "generate_until",
+            "generation_kwargs": {
+                "until": [
+                    "ASSISTANT:"
+                ],
+                "max_new_tokens": 16,
+                "image_aspect_ratio": "original"
+            },
+            "repeats": 1,
+            "should_decontaminate": false,
+            "metadata": [
+                {
+                    "version": 0.0
+                }
+            ],
+            "model_specific_prompt_kwargs": {
+                "llava": {
+                    "img_token": "<image>",
+                    "post_prompt": "Answer with the option's letter from the given choices directly."
+                },
+                "gpt4V": {
+                    "img_token": "<image>",
+                    "post_prompt": "Answer with the option's letter from the given choices directly."
+                },
+                "default": {
+                    "img_token": "<image>",
+                    "post_prompt": "Answer with the option's letter from the given choices directly."
+                }
+            }
+        }
+    },
+    "versions": {
+        "chartqa": "Yaml",
+        "seedbench_2_plus": "Yaml"
+    },
+    "n-shot": {
+        "chartqa": 0,
+        "seedbench_2_plus": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78/checkpoints/Xphi35-siglip224/SMOE/1M3/Full_remoe,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}