5e9d4c1ce4a0685e8f3ccbc7a62ba4a4c0f68dbd0f2f0ccf19e486d704144198

.gitattributes

@@ -287,3 +287,5 @@ sft/1M3/Full_xmoe/checkpoint-6893/logs/0628_2054_llava...l_mme_llava_model_args_
 sft/1M3/Full_xmoe/checkpoint-6893/logs/0628_2054_llava...l_mme_llava_model_args_1b5567/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
 sft/1M3/Full_xmoe/checkpoint-6893/logs/0628_2054_llava...l_mme_llava_model_args_1b5567/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
 sft/1M3/Full_xmoe/checkpoint-6893/logs/0628_2054_llava...l_mme_llava_model_args_1b5567/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_2212_llava...l_mme_llava_model_args_732fc6/infovqa_val.json filter=lfs diff=lfs merge=lfs -text
+sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_2212_llava...l_mme_llava_model_args_732fc6/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text

sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_1836_llava...image_llava_model_args_732fc6/rank0_metric_eval_done.txt

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

sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_1836_llava...image_llava_model_args_732fc6/results.json

@@ -0,0 +1,146 @@
+{
+    "results": {
+        "hallusion_bench_image": {
+            "aAcc,none": 46.0568,
+            "aAcc_stderr,none": "N/A",
+            "fAcc,none": 20.5202,
+            "fAcc_stderr,none": "N/A",
+            "qAcc,none": 17.1429,
+            "qAcc_stderr,none": "N/A",
+            "alias": "hallusion_bench_image"
+        },
+        "mathvista_testmini": {
+            "gpt_eval_score,none": 38.9,
+            "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 0x7fb8917690d0>",
+            "doc_to_text": "<function hb_doc_to_text at 0x7fb891769820>",
+            "doc_to_target": "gt_answer_details",
+            "process_results": "<function hb_process_results at 0x7fb8914d4040>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "aAcc",
+                    "aggregation": "<function hb_aggregation_result_aAcc at 0x7fb8914d49d0>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "qAcc",
+                    "aggregation": "<function hb_aggregation_result_qAcc at 0x7fb891420040>",
+                    "higher_is_better": true
+                },
+                {
+                    "metric": "fAcc",
+                    "aggregation": "<function hb_aggregation_result_fAcc at 0x7fb891420820>",
+                    "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 0x7fb8652c1b80>",
+            "doc_to_text": "<function mathvista_doc_to_text at 0x7fb8652cd280>",
+            "doc_to_target": "answer",
+            "process_results": "<function mathvista_process_results at 0x7fb864ec5940>",
+            "description": "",
+            "target_delimiter": " ",
+            "fewshot_delimiter": "\n\n",
+            "metric_list": [
+                {
+                    "metric": "gpt_eval_score",
+                    "aggregation": "<function mathvista_aggregate_results at 0x7fb864ed1040>",
+                    "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_xmoe/checkpoint-20679,conv_template=phi35",
+        "batch_size": "1",
+        "device": null,
+        "limit": null,
+        "bootstrap_iters": 100000,
+        "gen_kwargs": ""
+    },
+    "git_hash": "289c7fe5"
+}

sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_2212_llava...l_mme_llava_model_args_732fc6/infovqa_val.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:496fd03deb180629885ab9869037ab8f0b6285938f568fd6a1207d5059b679b9
+size 576440214

sft/1M3/Full_xmoe/checkpoint-20679/logs/0628_2212_llava...l_mme_llava_model_args_732fc6/mmbench_en_dev.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d30df724f343220fdbeb1a5eaf48d75e06533ed1d3b597a9d2d983b15506d6
+size 14568246