Upload folder using huggingface_hub

.gitattributes

@@ -359,3 +359,24 @@ sft/665K36/revise_Full_smoe_sharev3/checkpoint-12477/logs/0717_2000_llava...l_mm
 sft/665K36/revise_Full_smoe_sharev3/checkpoint-12477/logs/0717_2000_llava...l_mme_llava_model_args_82420a/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
 sft/665K36/revise_Full_smoe_sharev3/checkpoint-12477/logs/0717_2000_llava...l_mme_llava_model_args_82420a/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
 sft/665K36/revise_Full_smoe_sharev3/checkpoint-12477/logs/0717_2000_llava...l_mme_llava_model_args_82420a/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mathvista_testmini.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mme.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mmstar.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mathvista_testmini.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mme.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mmstar.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mathvista_testmini.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mme.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mmstar.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mathvista_testmini.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mme.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mmstar.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mathvista_testmini.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mme.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
+sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mmstar.json filter=lfs diff=lfs merge=lfs -text

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2142_llava...u_val_llava_model_args_861273/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2143_llava...u_val_llava_model_args_861273/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2143_llava...u_val_llava_model_args_861273/rank2_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2143_llava...u_val_llava_model_args_861273/rank3_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3bab9cc5ed7c089d9dc6fd7b61bbefdf945d5ef635cdf5121500ac690836c9e
+size 36750400

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/rank2_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/rank3_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2159_llava...u_val_llava_model_args_861273/results.json

@@ -0,0 +1,66 @@
+{
+    "results": {
+        "mmmu_val": {
+            "mmmu_acc,none": 0.39667,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        }
+    },
+    "configs": {
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f91978c0790>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f91977604c0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f91976f73a0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f91975f7310>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mmmu_val": "Yaml"
+    },
+    "n-shot": {
+        "mmmu_val": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-4159,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mathvista_testmini.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea24a08322e3d4261f46343ad938d9cee0240e86f63937df3a56af0f35b31db
+size 45280348

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mme.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ff23a00ca67cbf25c3913c38b6130c53471ff8ede1639ac638afab6dd079a0
+size 94629687

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6066f4915e0fe06637da76ce56045cb5c220d5f17687c9fa4c81f604f31555ad
+size 36750432

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/mmstar.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59eae9c9fd88fdf94ee4899dba7f649d4538bce9a912b884dcfe62d72d81e9f
+size 60426711

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2213_llava...mstar_llava_model_args_861273/results.json

@@ -0,0 +1,285 @@
+{
+    "results": {
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 24.4,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        },
+        "mme": {
+            "mme_cognition_score,none": 300.3571428571429,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1333.4614845938377,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.39667,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.6777537264839942,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.3289425202652911,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.5032956116682105,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.37952872210297955,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.2650193798449612,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.2725281195018929,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        }
+    },
+    "configs": {
+        "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 0x7f7d7e34c700>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7f7d7e354dc0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7f7d7e3614c0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7f7d7e36db80>",
+                    "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"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f7ddf039940>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f7ddd5dd160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f7ddd5dd700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f7ddd5ddc10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f7ddd5e60d0>",
+                    "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"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f7d90842700>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f7d907b1430>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f7d9067f310>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f7d90579280>",
+                    "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 0x7f7d7e27bd30>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7f7d7e2841f0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7f7d7e284700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e284b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e284f70>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e20a3a0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e20a790>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e20ab80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f7d7e20af70>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mathvista_testmini": "Yaml",
+        "mme": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml"
+    },
+    "n-shot": {
+        "mathvista_testmini": 0,
+        "mme": 0,
+        "mmmu_val": 0,
+        "mmstar": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-4159,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mathvista_testmini.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba84a4cbb0576f85800446579c3dcd431f37dd7139cdb6f7db6663823358fd2
+size 45272253

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mme.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011e40f78ee9008a61b460145cf49396d68e89126511bce959ec55b38e3f0158
+size 94631375

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f900a5b0df3eef25875d5833f0bc4b017bf4b6013ba00120ee1b519f1f2f05
+size 36750618

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/mmstar.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0937b93e04b8698a8f641913eb0ae96114a2bdf93057c229af5a93cf653bd2
+size 60427356

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2225_llava...mstar_llava_model_args_fc3596/results.json

@@ -0,0 +1,285 @@
+{
+    "results": {
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 23.2,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        },
+        "mme": {
+            "mme_cognition_score,none": 314.2857142857143,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1367.7411964785915,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.41333,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.676844470255589,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.3550294767870302,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.5366379757463484,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.3494995653411495,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.31132495767620066,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.2568647183257686,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        }
+    },
+    "configs": {
+        "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 0x7f92e5d69700>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7f92e5d72dc0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7f92e5d804c0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7f92e5d8bb80>",
+                    "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"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f9346a62940>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f9345006160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f9345006700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f9345006c10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f934500e0d0>",
+                    "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"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f92f886c700>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f92f8837430>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f92f876a310>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f92f8652280>",
+                    "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 0x7f92e5c99d30>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7f92e5ca21f0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7f92e5ca2700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5ca2b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5ca2f70>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5c273a0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5c27790>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5c27b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f92e5c27f70>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mathvista_testmini": "Yaml",
+        "mme": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml"
+    },
+    "n-shot": {
+        "mathvista_testmini": 0,
+        "mme": 0,
+        "mmmu_val": 0,
+        "mmstar": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-8318,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mathvista_testmini.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:843ba4f9777b2c69442aa0ea4e48e2845ed19bb9ed320b49c8647cc3da343c28
+size 45272419

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mme.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5033ba470671eeca7bf50fb890fbf8716c3cb6e2ac150839a8111b765e658d
+size 94631595

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47bd208990c79ee8ec97895fccc9d91a4b18e85291f2892d986c4839972eac86
+size 36750492

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/mmstar.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4829e00e1150da10de6554ddf43d0512f21f6ce92e6db3d896e4ca0cab1e669
+size 60427313

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2237_llava...mstar_llava_model_args_82420a/results.json

@@ -0,0 +1,285 @@
+{
+    "results": {
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 23.7,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        },
+        "mme": {
+            "mme_cognition_score,none": 321.7857142857143,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1418.2278911564626,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.41222,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.6918706627011363,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.3625644804716286,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.5205089434882838,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.3660535284297661,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.28080727078321305,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.19842818316868963,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        }
+    },
+    "configs": {
+        "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 0x7f00a1460790>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7f00a1469e50>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7f00a1475550>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7f00a1481c10>",
+                    "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"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f010216f940>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f0100713160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f0100713700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f0100713c10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f010071b0d0>",
+                    "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"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f00b4139790>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f00b40664c0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f00b40123a0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f00b3f3a310>",
+                    "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 0x7f00a138edc0>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7f00a1398280>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7f00a1398790>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a1398c10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a131f040>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a131f430>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a131f820>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a131fc10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f00a1324040>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mathvista_testmini": "Yaml",
+        "mme": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml"
+    },
+    "n-shot": {
+        "mathvista_testmini": 0,
+        "mme": 0,
+        "mmmu_val": 0,
+        "mmstar": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-12477,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mathvista_testmini.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c597f6e7990da8a6152fa835b8fb94f55ffdf7abd8c89e3f77272a9574aa9099
+size 45275763

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mme.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1013eec1a07465ff759dc3031c2921cb4081bcc386e98c43120cc47847ee69
+size 94631509

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4026a47ec71284e1d594a154cb844d5aeaba76ce68754ec9b86d52078f260021
+size 36750611

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/mmstar.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ccf81f0fb7a589e721f551930e15431159b8a722590a0146130265df917a3ca
+size 60427594

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2249_llava...mstar_llava_model_args_fe2b4a/results.json

@@ -0,0 +1,285 @@
+{
+    "results": {
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 24.0,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        },
+        "mme": {
+            "mme_cognition_score,none": 324.2857142857143,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1410.4883953581434,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.42222,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.6964404085200243,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.3732928027511668,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.5295256540272851,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.375954518528776,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.3063853247794707,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.23852115038371227,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        }
+    },
+    "configs": {
+        "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 0x7f0e528ca700>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7f0e528d3dc0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7f0e528e14c0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7f0e528ebb80>",
+                    "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"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f0eb35e6940>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f0eb1b8a160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f0eb1b8a700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f0eb1b8ac10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f0eb1b920d0>",
+                    "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"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f0e650c3700>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f0e6507a430>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f0e64f7a310>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f0e64e31280>",
+                    "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 0x7f0e527fcd30>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7f0e528021f0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7f0e52802700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e52802b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e52802f70>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e527893a0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e52789790>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e52789b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f0e52789f70>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mathvista_testmini": "Yaml",
+        "mme": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml"
+    },
+    "n-shot": {
+        "mathvista_testmini": 0,
+        "mme": 0,
+        "mmmu_val": 0,
+        "mmstar": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-16636,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mathvista_testmini.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86378d064486a95db78016ad5425190064d153e0f9021768efc7fa43820edd8c
+size 45276045

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mme.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a82efa94480755a72c2a10eda7fb180405a023f189abefceb5ffb7063f342426
+size 94631601

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mmmu_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c498ee36877cbd7e8a0700b0d8e55d660a8b97813d5104e13a420f69cd4e9b
+size 36750667

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/mmstar.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5965c6560c55dd4db61a68e735a651305207df081f43f026b6c609641ccd2348
+size 60427706

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/rank0_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/rank1_metric_eval_done.txt

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

sft/665K36/revise_Full_smoe_sharev3/analysts/0717_2301_llava...mstar_llava_model_args_fe4e53/results.json

@@ -0,0 +1,285 @@
+{
+    "results": {
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 24.0,
+            "gpt_eval_score_stderr,none": "N/A",
+            "alias": "mathvista_testmini"
+        },
+        "mme": {
+            "mme_cognition_score,none": 305.3571428571429,
+            "mme_cognition_score_stderr,none": "N/A",
+            "mme_percetion_score,none": 1400.8141256502602,
+            "mme_percetion_score_stderr,none": "N/A",
+            "alias": "mme"
+        },
+        "mmmu_val": {
+            "mmmu_acc,none": 0.42444,
+            "mmmu_acc_stderr,none": "N/A",
+            "alias": "mmmu_val"
+        },
+        "mmstar": {
+            "coarse perception,none": 0.7007139127935286,
+            "coarse perception_stderr,none": "N/A",
+            "fine-grained perception,none": 0.36133628101203635,
+            "fine-grained perception_stderr,none": "N/A",
+            "instance reasoning,none": 0.5332709723793451,
+            "instance reasoning_stderr,none": "N/A",
+            "logical reasoning,none": 0.37952487556447956,
+            "logical reasoning_stderr,none": "N/A",
+            "math,none": 0.2904916243428673,
+            "math_stderr,none": "N/A",
+            "science & technology,none": 0.2396233390154238,
+            "science & technology_stderr,none": "N/A",
+            "alias": "mmstar"
+        }
+    },
+    "configs": {
+        "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 0x7f60bd21f700>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7f60bd228dc0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7f60bd2364c0>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7f60bd241b80>",
+                    "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"
+                }
+            }
+        },
+        "mme": {
+            "task": "mme",
+            "dataset_path": "lmms-lab/MME",
+            "dataset_kwargs": {
+                "token": false
+            },
+            "test_split": "test",
+            "doc_to_visual": "<function mme_doc_to_visual at 0x7f611df29940>",
+            "doc_to_text": "<function mme_doc_to_text at 0x7f611c4cd160>",
+            "doc_to_target": "answer",
+            "process_results": "<function mme_process_results at 0x7f611c4cd700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mme_percetion_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f611c4cdc10>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "mme_cognition_score",
+                    "aggregation": "<function mme_aggregate_results at 0x7f611c4d50d0>",
+                    "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"
+                }
+            }
+        },
+        "mmmu_val": {
+            "task": "mmmu_val",
+            "dataset_path": "lmms-lab/MMMU",
+            "test_split": "validation",
+            "doc_to_visual": "<function mmmu_doc_to_visual at 0x7f60cfa0b700>",
+            "doc_to_text": "<function mmmu_doc_to_text at 0x7f60cf9bb430>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmmu_process_results at 0x7f60cf8b3310>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "mmmu_acc",
+                    "aggregation": "<function mmmu_aggregate_results at 0x7f60cf834280>",
+                    "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 0x7f60bd150d30>",
+            "doc_to_text": "<function mmstar_doc_to_text at 0x7f60bd1581f0>",
+            "doc_to_target": "answer",
+            "process_results": "<function mmstar_process_results at 0x7f60bd158700>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "coarse perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd158b80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fine-grained perception",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd158f70>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "instance reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd0de3a0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "logical reasoning",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd0de790>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "science & technology",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd0deb80>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "math",
+                    "aggregation": "<function mmstar_aggregate_results at 0x7f60bd0def70>",
+                    "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"
+                }
+            }
+        }
+    },
+    "versions": {
+        "mathvista_testmini": "Yaml",
+        "mme": "Yaml",
+        "mmmu_val": "Yaml",
+        "mmstar": "Yaml"
+    },
+    "n-shot": {
+        "mathvista_testmini": 0,
+        "mme": 0,
+        "mmmu_val": 0,
+        "mmstar": 0
+    },
+    "model_configs": {
+        "model": "llava",
+        "model_args": "pretrained=/cm/archive/namnv78_new/revise_checkpoints/Xphi35-siglip224/SMOE/665K36/revise_Full_smoe_sharev3/checkpoint-20791,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}