diff --git a/vmllm_cached/qwen3vit/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/qwen3vit/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0dcb20d2498396aa3f06c72c22d37e267dda5f71 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde6c7cd2ce6c46b02dec2761a3aad5040dc692cce2c7f97f505767f4c53a880 +size 69352320 diff --git a/vmllm_cached/qwen3vit/image_10pct/train/dataset_info.json b/vmllm_cached/qwen3vit/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/image_10pct/train/state.json b/vmllm_cached/qwen3vit/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5ca15cb1aa8769a8ceda2454630e7dae9f992c56 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "7cd6dba47f471540", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/image_full/train/data-00000-of-00002.arrow b/vmllm_cached/qwen3vit/image_full/train/data-00000-of-00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d2c621c6dcdd6ded1120d14449ca5f9afb698986 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_full/train/data-00000-of-00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242b7e98f62eb717313586119a386c5911a1d42d7910f6b0db37e549ba97b86b +size 347798136 diff --git a/vmllm_cached/qwen3vit/image_full/train/data-00001-of-00002.arrow b/vmllm_cached/qwen3vit/image_full/train/data-00001-of-00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6135b11efe0f3a9bd88c2ed70c73b44df8c42947 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_full/train/data-00001-of-00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66b7932b167a90d96a6ec07e778c0d0a8995a92a7f8b3a7d10db420daa35b08c +size 348273776 diff --git a/vmllm_cached/qwen3vit/image_full/train/dataset_info.json b/vmllm_cached/qwen3vit/image_full/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..985bfb44ff560f86c3f64cdc19c125952c425637 --- /dev/null +++ b/vmllm_cached/qwen3vit/image_full/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 663687137, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_full_v800k_sharegpt.json": { + "num_bytes": 856061267, + "checksum": null + } + }, + "download_size": 856061267, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 1519748404, + "splits": { + "train": { + "name": "train", + "num_bytes": 663687137, + "num_examples": 738590, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/image_full/train/state.json b/vmllm_cached/qwen3vit/image_full/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b09f3c2a4f23fa905ea9928e92c841cbbf4ff34f --- /dev/null +++ b/vmllm_cached/qwen3vit/image_full/train/state.json @@ -0,0 +1,16 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00002.arrow" + }, + { + "filename": "data-00001-of-00002.arrow" + } + ], + "_fingerprint": "8897283c77da70ab", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/video_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/qwen3vit/video_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e56955b9353204c921694a632eec6e5d1d7f8f46 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3ccc9ed7d1ce2b304f7d545abb611b12457518489aad44732008430eb33e83 +size 157175192 diff --git a/vmllm_cached/qwen3vit/video_10pct/train/dataset_info.json b/vmllm_cached/qwen3vit/video_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..48fa342a8591816ebce4f1851e6641c515d25c12 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_10pct/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 153484834, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_small_10pct_sharegpt.json": { + "num_bytes": 173305720, + "checksum": null + } + }, + "download_size": 173305720, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 326790554, + "splits": { + "train": { + "name": "train", + "num_bytes": 153484834, + "num_examples": 113615, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/video_10pct/train/state.json b/vmllm_cached/qwen3vit/video_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..187097c668dc2aabb4a0392a8d0b753f748f2285 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "2700a2518587c720", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/video_full/train/data-00000-of-00003.arrow b/vmllm_cached/qwen3vit/video_full/train/data-00000-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..08fc44f419f67821963d4fd8b0e453a8ba034e63 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_full/train/data-00000-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b88beff00c56b12f30267dba6013ff4a41c5b3a0b5cf0bc2192a2958e315fbf +size 354565576 diff --git a/vmllm_cached/qwen3vit/video_full/train/data-00001-of-00003.arrow b/vmllm_cached/qwen3vit/video_full/train/data-00001-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..cdd01b4e43c11d3eadfd7d4ce8bfd5805dab0e01 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_full/train/data-00001-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aea108e61e829dbb4b25d191ac19b52f5e5fbea5bfc5c9669a88ef249d9f325c +size 354296560 diff --git a/vmllm_cached/qwen3vit/video_full/train/data-00002-of-00003.arrow b/vmllm_cached/qwen3vit/video_full/train/data-00002-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..71720e43ee57171816988d91abb977a879ce0f22 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_full/train/data-00002-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f12a9db322e5c1237684efe23b4612a2044b3ef2dbd74f96a3a447de8b24991 +size 354842288 diff --git a/vmllm_cached/qwen3vit/video_full/train/dataset_info.json b/vmllm_cached/qwen3vit/video_full/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7016ae1315aa291acef19464b150544de3803b99 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_full/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 1037696374, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_full_v800k_sharegpt.json": { + "num_bytes": 1177312903, + "checksum": null + } + }, + "download_size": 1177312903, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 2215009277, + "splits": { + "train": { + "name": "train", + "num_bytes": 1037696374, + "num_examples": 800001, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwen3vit/video_full/train/state.json b/vmllm_cached/qwen3vit/video_full/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..380e6564adb820c18ad41147fc9b24d535a52695 --- /dev/null +++ b/vmllm_cached/qwen3vit/video_full/train/state.json @@ -0,0 +1,19 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00003.arrow" + }, + { + "filename": "data-00001-of-00003.arrow" + }, + { + "filename": "data-00002-of-00003.arrow" + } + ], + "_fingerprint": "4c41ef3382480e1b", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/qwenvit_v4_1/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b9912dcbf1af8dfade9c37fe72bfcc22984d31b6 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b30ec6ac4ecd10f6af680df3ddbba35278bd2a1834899de7aed1dbf5fd229ee +size 69352320 diff --git a/vmllm_cached/qwenvit_v4_1/image_10pct/train/dataset_info.json b/vmllm_cached/qwenvit_v4_1/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/image_10pct/train/state.json b/vmllm_cached/qwenvit_v4_1/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..ebaa7c1e08eee5bf9fbd28b5f619971a901daf02 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/image_10pct/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "1ee927233338c5f1", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/image_10pct/train/v3_patch_meta.json b/vmllm_cached/qwenvit_v4_1/image_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ab9e5f2f136d6fafec16abc6af2e4b75d2956b44 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/image_10pct/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v4_fast", + "mode": "image", + "from": "qwen3vit (Qwen3 ViT base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 (= 16 frames \u00d7 1) * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/qwen3vit/image_10pct/train", + "rows": 73859, + "lengths_sample_mean_old": 2624.35, + "lengths_sample_mean_new": 2625.35, + "timestamp": "2026-05-06T09:22:26" +} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/video_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/qwenvit_v4_1/video_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..24ce8b2812f59a29dcba3a4c20edfa3b2c558723 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/video_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2d9f8240d1319817225d0697d1a2e43eed9c1f022ddd38cd73fa0e802d86a9 +size 157175192 diff --git a/vmllm_cached/qwenvit_v4_1/video_10pct/train/dataset_info.json b/vmllm_cached/qwenvit_v4_1/video_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..48fa342a8591816ebce4f1851e6641c515d25c12 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/video_10pct/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 153484834, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_small_10pct_sharegpt.json": { + "num_bytes": 173305720, + "checksum": null + } + }, + "download_size": 173305720, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 326790554, + "splits": { + "train": { + "name": "train", + "num_bytes": 153484834, + "num_examples": 113615, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/video_10pct/train/state.json b/vmllm_cached/qwenvit_v4_1/video_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e94516b371488839bd84dba0e05a65bdfd10bfe6 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/video_10pct/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "9c3dccfcc84579a5", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/qwenvit_v4_1/video_10pct/train/v3_patch_meta.json b/vmllm_cached/qwenvit_v4_1/video_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..5e58e64ce0dc4306c34453ff0359d10ba3c16491 --- /dev/null +++ b/vmllm_cached/qwenvit_v4_1/video_10pct/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v4_fast", + "mode": "video", + "from": "qwen3vit (Qwen3 ViT base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 (= 16 frames \u00d7 1) * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/qwen3vit/video_10pct/train", + "rows": 113615, + "lengths_sample_mean_old": 2568.1, + "lengths_sample_mean_new": 2584.1, + "timestamp": "2026-05-06T09:22:27" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00000_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00000_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bfa76d51eca010fdde3cc44bd5bd4793a8cd053e --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00000_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6196ec385d9b4e7345034bf80c853e33850054fddca0993796946cbb6511d4ce +size 4348624 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00001_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00001_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1739910166f77c8b79568e53ef274a8e9543e470 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00001_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2abec3e42edcea0486bd90f8b09427102fa26553e897a556b289f981c071f482 +size 4397128 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00002_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00002_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..61362c74de4d24e58a47c5048ffd464e77235491 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00002_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a10416252759d5bed49dbacb73833a08a7bf3d4582feef0312d52b53f34f5316 +size 4337304 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00003_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00003_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a92ee62eafcf220459bfb74628aafd543a8c454b --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00003_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c249788d8710e351652e7d7b56c11ff6e843d06361d40da024b95fe431d6f79 +size 4294744 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00004_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00004_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e0694d1491fdef2c3276e04fb74926a80b7a221f --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00004_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ae9e64e766bd13e39a466fecdd6fb29d85177df30cd3de0582061f037530ea8 +size 4317096 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00005_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00005_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2d9020d7cd090098626c185065f4d187bd66fa43 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00005_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:771c2d9c3297ff6fcd68224d32c93d6d953648963bec19146e11f839f6737ab6 +size 4366920 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00006_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00006_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0b1e7f720ae504afc8bdaaefcef2d7b283ed57c8 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00006_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2615d1d49510237a6b5668ebb113e3a5fcd3a1c4aa7fd47ee518eb0d60d8d32b +size 4356176 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00007_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00007_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..916eda73d8b23e2b538e4c25a3deaacf7eb6f31e --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00007_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65edab8224984e90875355653bbbc1ec5956d5968cc124131c446cb2ffde792 +size 4407040 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00008_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00008_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..63db33775ec7f224549b6639c3d88e905c69bf61 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00008_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3e76a89f1f7c158e7385f2993a90791d6177626649273984a6a085e0dd63bac +size 4347048 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00009_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00009_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..062c0f1f536de025325dcc6bbeeffd4d93c569fd --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00009_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602f2c58b4c39ca17d7ca19622e1971f218bd54177cbf15c45a9daf1725ed63c +size 4314704 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00010_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00010_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e721bc8cb72e68961ee2b542a818870882bb0194 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00010_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d0fc9c580d736e3d17c41009f855aeb4c3bb81a3ceaef3ce33ee832bfc5c9e +size 4371096 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00011_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00011_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7d95b9e29b679f7d9694955655d03c815b292caf --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00011_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b35f857402134fe8a314a3f61b698fd1c76db54529f934af00f101620f62b2f9 +size 4369816 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00012_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00012_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b192ab2d1d35d065bbb66d01ac212c08dffd7ce4 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00012_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bed79f4d3726d77649dc3ae1ba46c2cea36fe17d087b76df889e3f829a123bd +size 4378360 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00013_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00013_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ce8fa24f160747a2a2fa3539587efd44f6c37d6d --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00013_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b977b503d2d0c8730947f76b284daa697a3cfc31508c959e0f79ee48b77b5b7 +size 4362504 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00014_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00014_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..62b61b7d9ff95b9090d3bfe5d812226d5aab4030 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00014_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a19a02543444662722d5a6971f2ba9a04995e9a82efe79cd8622ec4d9c48f4fb +size 4452368 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00015_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00015_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..996834b1429e9f99500cfd3d8cd664f58b197ede --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-293d2d32c7066ab2_00015_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:690cdb0c532447190c7ab6baf54e28f886cc84c7fb764ca1bb2c8bf5d3440c8e +size 4372144 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00000_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00000_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..39bd5e82f4bd7f8cb65e64bf1db660413f3901aa --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00000_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bdbbea67ca3da6665cbed5aafc75cffa0fc2489bfb3147bb33ab9eab3685a76 +size 4348624 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00001_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00001_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a159400f6614b5f4a9694a0dd03c8fd1ac05e416 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00001_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9947ccb4fbd7e237a47c62afdcba358fd1f70ccdafa2b75e0901adc04d54f110 +size 4397128 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00002_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00002_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..059f066cd4e18ec0888f6cef4e3deeddf4c782f8 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00002_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ff06c350c38b02e83f34543cd2a4c4c9112a2e020bbca185ad8536f40411a6 +size 4337304 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00003_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00003_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5512beec3fe922acceb43d070caba27290dc620a --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00003_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a02edb69066ef0eb0e3763102886a2c635a8d4cae4349c152f8f9e0a9742840 +size 4294744 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00004_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00004_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f8cb1e349fb9eb99479d44d6549cf7c04a32ae7b --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00004_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3933f3f36ec0a176758430e57d3cfa356d4e06aa0c50de03b94a71d591148fd0 +size 4317096 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00005_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00005_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..789eecacd3243c48857e1c686726793ed2784d85 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00005_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9baa6891e3b6a8254d8a897694984b5c1314ca9cd403f0063c384d52b2a84307 +size 4366920 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00006_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00006_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..177af87e6da5a9a6e900c0cf97a0524ff866d8a4 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00006_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b67cbee268f6706ddec761821f9c4cf4639125fe2386920c6a19af06244546a +size 4356176 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00007_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00007_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..13b7884745b70ef89d07b0ed0b2cd20c1d1f6bc8 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00007_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b11634a8f510b85116d2b629a251588b5d8d79ba4ca33d49f9703bfa1d49f61 +size 4407040 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00008_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00008_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7f2309391adbe16cc14b0d45536eaf3952cf8aca --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00008_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b7b1b323d4af133985be1062d316eb0a2cfdf975d8ebaf6a6f85c485a62c87 +size 4347048 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00009_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00009_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b5cdc60a4e0ce48f4d166dddc0778174e7fa56b1 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00009_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9e828b05b7a7d3aaf2e8a432003aefa9a9785ac82473de01d160dc63dd59ba +size 4314704 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00010_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00010_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3cdf244e3455999c74701cdbb467a191765cdc00 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00010_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2bdd212e2bbb3add2c91f167be38f6a8014fecbb0b1b9bf77e056d4723f6077 +size 4371096 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00011_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00011_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..51bd78cd8052db9acb49df67124d110ee990b8ec --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00011_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caa8a6745a1f8bbe73e90ae936162b6a151305785b1d4aeb2a610110e96fde56 +size 4369816 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00012_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00012_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..01c5c3cdf120bf1784c9964d028a5a3fee3cd6a9 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00012_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c787452bbdff9c9a739d6579a5d2a393bd717e7fc80739a677d36348f5b35d87 +size 4378360 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00013_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00013_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5526851d6945a2cf00d6a39cd936e28a1f5d5b5c --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00013_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd7fcc84d11fe36a966f7fd57d6b754d0f135eddc903ba2bc52e251427352e9 +size 4362504 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00014_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00014_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c4f1937d4dda750ffae6c7ce91ae3cb7a9e65377 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00014_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c583c4de13a0e7ac8e888693b1e42c20e6127424e58698ebd055a4b0664bd6f +size 4452368 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00015_of_00016.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00015_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..fe8dd520edb4a07db806f52c87ef717a3e5ee4fc --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-2b2dbbebf1aceb79_00015_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbc959973c44860ec5a17611b2d4579e2e7c84bec45e93c99da248ec4a81a7b +size 4372144 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00000_of_00002.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00000_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7522d3ec1096b7878b86450b310d4f9468a0fa4c --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00000_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985bb72a0d79952df7c252f75bc6f99c38f5ca05c45256bc593dfc6274b7a0d4 +size 4128 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00001_of_00002.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00001_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..51434409ae4caa25a1e8d27287c2622ed514a92f --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-33d221812f79bfbc_00001_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4d4c269735e9f01584edd873716e39ce6d390aa9fe05c77585dfe1416992e3 +size 2280 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00000_of_00002.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00000_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2070a402f22a810d2ee9205cba9663da374ba574 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00000_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b220aa4773d75eaf20380dd2bea929714e3ea39ed52030b9c03b9451d8be90c +size 4816 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00001_of_00002.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00001_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ac6023f0e804bcc60f4726fcdcb792dfa47b1101 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-8000b143bd29da8c_00001_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:773133ef9171ff92e58e0fd1ef8b021699a3d1abd07f2ec7425fa64447c91e64 +size 6552 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00000_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9e80a777b770c3d08a01150825bba1c1fc527771 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bc3855378ba0c22934c717bb5ace72e31cc2fa1b11c621ad25e65e533fe9fe +size 15416 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00001_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d46c6812e8656fdf1d47d7c5ef9a869252612bd0 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:269147c25c10e3112bb2d9463b63187090c2c0187423274652ddfadb85a2da4f +size 13008 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00002_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8c3222ba70979f5869e329d8c58ab86dda9fcef2 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15d170f2a75fd779b873daccc1b894104a1bfcc5ce8c4bdb21f0492ffc8fcf7 +size 13800 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00003_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3ccd383f6712ca353af9ed2ec3c397ee16e40760 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-a126ba2e9d91ca03_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e77bb23367273d5970f57bfa5d8a98b1fbf809f31a50fa0a30e1d370d88ddce +size 13360 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00000_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8014d67a690bb6cbb12ee17a431cee723dad6883 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1e72427e455c480172bce46ac45ef8b888bbdda7a2d94852f6b6ecd18fed01 +size 15416 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00001_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4840bce635d24ea23045c372d45092d221b52330 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48899a1dc3fb1dcf3b243115632b5b424002d13b395e4ac8c4a52d10fc89a811 +size 13008 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00002_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..78cff490c8c9e9c6f76d5d7df0b5c55f9238a5ce --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1cc10580c604b3f61f5cf9ac8eb0ea684858ec25d3b269601de0d672ac0318c +size 13800 diff --git a/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00003_of_00004.arrow b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c49daf4ebdc8e823027371885f9a09401eae4496 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/cache-c27c6f1780172288_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce89920b7194f03756e878e88831a2d1ee9d594e204de13dcd8d9d3dcfd243cc +size 13360 diff --git a/vmllm_cached/siglip2/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4dbad8d0cf03ad1a0c05435b43040802d4a6a318 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5f2d921f765fc0f4e0a177d7b03e0780fdc8ddf7e3c0dcfce9ee00d69ddbd15 +size 69352320 diff --git a/vmllm_cached/siglip2/image_10pct/train/dataset_info.json b/vmllm_cached/siglip2/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_10pct/train/state.json b/vmllm_cached/siglip2/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..1eef6bf77a106b15062e048c45d926f18c9f737b --- /dev/null +++ b/vmllm_cached/siglip2/image_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "2b4be503b5c839e3", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_15pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/image_15pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..02fc00b8a108d6e89f35d26346e40204d7ae74af --- /dev/null +++ b/vmllm_cached/siglip2/image_15pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c721704969759e8cc5c3a96f08c885f2abc94ad8a813f14e2873b42dc68c6f70 +size 104310120 diff --git a/vmllm_cached/siglip2/image_15pct/train/dataset_info.json b/vmllm_cached/siglip2/image_15pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e88efa6074b9bf6d46b572a17be2cf40ad5c046e --- /dev/null +++ b/vmllm_cached/siglip2/image_15pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 99458104, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_15pct_sharegpt.json": { + "num_bytes": 128265396, + "checksum": null + } + }, + "download_size": 128265396, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 227723500, + "splits": { + "train": { + "name": "train", + "num_bytes": 99458104, + "num_examples": 110788, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_15pct/train/state.json b/vmllm_cached/siglip2/image_15pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e92c92463d6487124ed01bd14a38c4a2d71a2e31 --- /dev/null +++ b/vmllm_cached/siglip2/image_15pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "0b05f0d2e082b7de", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_20pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/image_20pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e15ec54f63f3e7e8a1646a2ba8c6ec5b2967aa09 --- /dev/null +++ b/vmllm_cached/siglip2/image_20pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bba6ba90d16db9c84cf288aa39c350e969ac212fdb7075e06ba40491a1b7fe9 +size 139214336 diff --git a/vmllm_cached/siglip2/image_20pct/train/dataset_info.json b/vmllm_cached/siglip2/image_20pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..bf3a481717f114dad445c891a4ba243d29b5d6f2 --- /dev/null +++ b/vmllm_cached/siglip2/image_20pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 132733591, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_20pct_sharegpt.json": { + "num_bytes": 171232803, + "checksum": null + } + }, + "download_size": 171232803, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 303966394, + "splits": { + "train": { + "name": "train", + "num_bytes": 132733591, + "num_examples": 147718, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_20pct/train/state.json b/vmllm_cached/siglip2/image_20pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..49d7d70499e7d500bb4baa10a32d8097dfb70611 --- /dev/null +++ b/vmllm_cached/siglip2/image_20pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "859fa0aafac7fffc", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_full/train/data-00000-of-00002.arrow b/vmllm_cached/siglip2/image_full/train/data-00000-of-00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..94ef2c179ae5ca0a4682bd82ce764f0847254de1 --- /dev/null +++ b/vmllm_cached/siglip2/image_full/train/data-00000-of-00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf92cfb1ae2fa566a38e6608914e7ff51bf64ee5db0d5d1e9d859d963290fd87 +size 347798136 diff --git a/vmllm_cached/siglip2/image_full/train/data-00001-of-00002.arrow b/vmllm_cached/siglip2/image_full/train/data-00001-of-00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c9316ede74940e749d3486fc628e9832d962f6de --- /dev/null +++ b/vmllm_cached/siglip2/image_full/train/data-00001-of-00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a84cbfe97434f69f74ba3c2fb8e24391ac66dec625f17bd6f539b82cdcb08f +size 348273776 diff --git a/vmllm_cached/siglip2/image_full/train/dataset_info.json b/vmllm_cached/siglip2/image_full/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..985bfb44ff560f86c3f64cdc19c125952c425637 --- /dev/null +++ b/vmllm_cached/siglip2/image_full/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 663687137, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_full_v800k_sharegpt.json": { + "num_bytes": 856061267, + "checksum": null + } + }, + "download_size": 856061267, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 1519748404, + "splits": { + "train": { + "name": "train", + "num_bytes": 663687137, + "num_examples": 738590, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/image_full/train/state.json b/vmllm_cached/siglip2/image_full/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..d36e6ebc89167d398a19562d36f86a1093764b09 --- /dev/null +++ b/vmllm_cached/siglip2/image_full/train/state.json @@ -0,0 +1,16 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00002.arrow" + }, + { + "filename": "data-00001-of-00002.arrow" + } + ], + "_fingerprint": "9fe766c598ce8d41", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00000_of_00002.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00000_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..be13fad7ec898be27e56c407aa7536b8a8fce11f --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00000_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20273a31a18f92fc6d7980211816e3227fe9f2a773675b4b7e76e9fb094319aa +size 6800 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00001_of_00002.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00001_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6c335b090ccf0e5d6976a87e1c2b2384d1196cbf --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-7b59f7c85479c239_00001_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14300b36ab29213655ca854e6f2ae9ab75069ed6aa08be5e889f0ac287262722 +size 6200 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00000_of_00002.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00000_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ff39979667415efc13bae136f7725e2247b15fdf --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00000_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a5229a50fd58fb95481a8ae59d031b681c96af549a8cab571dda12ef88119f4 +size 4664 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00001_of_00002.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00001_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..be6d642979c4d5608c21ca1c5a27b1cc7f194b09 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-b56e8ce4ee04fa7d_00001_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab83c8b458dcdd628db1195312c86a73bf30962844a9e5b1253f411655589d4 +size 3696 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3cb42af124157b9951281d6290df163b230e1af8 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37e12a75f8290bdc6ada435b21f68a737601a918a61c7e4a0e28a7963d7d491 +size 1946512 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a954829fa9db5eccd692485c3c87c362e8795acc --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d3241c15f1f584b178084016de472a24b5956cab33c1a8dd63a44178d670bb +size 1967768 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5a55cd31e4e615d3d13d2bfd4feff9e51c9fb367 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1315bcfa71de8000055ace237290ffc4cedb8487376cfb3acdf8f68fe9ddde +size 1952400 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3186629613de9d6d7c37a4a67d8954a63f0c8231 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/cache-fcbefda1c6f39fdf_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:964e970febe8c3ae69b4f5da2f59884c3a455add2776f82ef3133d49edc3b4bb +size 1975104 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6036385b65af7cd6ae89d2d9beeed75105696dd6 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f58c7494acfd6c99e9e43ad6cc1000d4c76f48de4f18e7c3a7ca71cfea04b3e +size 7837872 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b59fb25a630e78cdaca99936940baa155b04ec05 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7447721, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_00.json": { + "num_bytes": 8441128, + "checksum": null + } + }, + "download_size": 8441128, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15888849, + "splits": { + "train": { + "name": "train", + "num_bytes": 7447721, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..8ba281bd867d09fe3f2eeb14de065ee6caccddd4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "79d93700ee4b5e2e", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8abfe2eb566a1b28f27fd6dfca44816b58ef453c --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10934b4a7229b276bd4f5fb602810efc6b27de98ec4bed3578f464311cd9bb47 +size 1938368 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4ff8c0b10f081af6c12cd42f67b58281ff917bbf --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f939edde493bb1a8aa74d62ecbcc474adc7c3badb3ccba6dd86290d1054cd6c +size 1933560 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0d91b06f5147ea77d9659149a1348b1b0f17ea26 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1684a17b863ac7a5ce71b7129b1275590cf7900ab17e3fe9fb5014cdb7a14f81 +size 1979440 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..73316e64990b82f5f82e8841c62651120b6009a1 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/cache-a52ede1910efd117_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfc7f5f518be5e553e041d28926c880ff51349a973d2d180cf4f13d5c440cc5 +size 1912880 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e4e88aa9c1c3f64eb748e80c30f7fdcd5a7c6acd --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd19aad8a470866476ad7d4a5ced3bb0d74a02af579e030fd9d8852f26a6eea7 +size 7760272 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..9753431187f753de6088f363a3c32dc44a55eac6 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7368826, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_01.json": { + "num_bytes": 8374839, + "checksum": null + } + }, + "download_size": 8374839, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15743665, + "splits": { + "train": { + "name": "train", + "num_bytes": 7368826, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..4dae48f6c070799693a5c7d47a8bb6edfeecb789 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "c7e2582a1bf58aa2", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4190e6b2e81c7186c6da8ba4ddaaa0deeac78ab8 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aa0febff711eae1f55b98fecfc47f13bba5822f8e7bd510371a594202a3cb9e +size 1912344 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..421776a73f026ae54b1c8fea0d42304f1c18485d --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84be659991d67ac94ef7b32e26c89bc0bc474df6afbfb7178a5b3791de80891b +size 1993944 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a414eea8667f1e2fca39e39dd5bc5d2cc7dc3b00 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c7ade3e8e768d46e949bed2efa8d8a7af82a10239298dd2b147d165608d1d1 +size 1974928 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b662528fd84b7cde759abbcc7f59dbb6d6015e47 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/cache-31ec45621acf1bed_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0fdc35fa27dfddb0462be535ee6b0c7570814bbf4b7c66aff3bd582274c9b4f +size 1976216 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6365fa236572b1f96f50a5bc3a259875fe91e410 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69aaa2bd2b90ba92286034c72790526ab9d490da818bbc829763838c7d31472e +size 7853432 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6f954de72e7e74d0f41e01d288d7974880fca499 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7463924, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_02.json": { + "num_bytes": 8451092, + "checksum": null + } + }, + "download_size": 8451092, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15915016, + "splits": { + "train": { + "name": "train", + "num_bytes": 7463924, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..06d2c5a294fe9781c18a2571d2bfbd2281cdbba1 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "de3e7648a7e0fde6", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..701b31d82813b3f56ff91c342e8c50d36d1f63bb --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cb962034e24aa4eab9def740bec77a679573e0b2faef7cfaaeb11c9cbff0bc +size 1977200 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..116fef2c5709d83e884e67812ca9aaf70dc1d3de --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a213bad486449a4bf306d2d579b0f81573217abcbe487e1baf6777709ff0dfc +size 1999168 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9018f8b31244c567eec5f810791aabf767a2091d --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84ee9abf51d0baa829b839dff1a4894e088e856d9126795248ead41b7bed5837 +size 1961672 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..79297d1c7346c4152f9bc66c3b3bd6563a78cc8e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/cache-0ce981fc8ef9745d_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fd459cf7b8564bf2809a60b7cca7df5101335af666e430cad8b307ac1fcc87 +size 2000016 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9b16961cf3e741c8f10aeeacea89a9e9e5bd53d4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536114808673bc1ce3b0fdb6b49ec45b44d8ebb56881a57b5d40ca8af1f0b6a7 +size 7934096 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7857d783c3661746d540b0aefc631a9bf2e0598b --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7544302, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_03.json": { + "num_bytes": 8531728, + "checksum": null + } + }, + "download_size": 8531728, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16076030, + "splits": { + "train": { + "name": "train", + "num_bytes": 7544302, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0623d80d36b3798cd6fd05690de13559c765853e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "24068e7a29948f2d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..fd44214dce001c15cdd9547b34444c2ae47ed486 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b99a249f1480bdaffe8e976ee648927607ca95090e358925ff0f16684180842 +size 1931320 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..65430e4c415b8350bf749a07bd3e2c39b42f64dc --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a14232475225f3b6a6fbbbebe73ecc373a50d6233792106795d4ea33f556879 +size 1932656 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..017cb4dd94b29b435f41cd658c10596f4415d60c --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3df45297ed7095a1ef2ded90ef0a2b247f20a00a295ff1a8e5e185000bc93f +size 1873072 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..05ffbefa29a9072dc0edacd05e6f874aeece16b7 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/cache-a01c95013bb3b632_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6142975da3fa8fa4a48c98f719f8e94df1fbced8edb82e80ee6049f5467d9bd8 +size 1943496 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..85e082f45feedfad755db20fbbdafa6300e9305e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cf57bff498d8f139d66fd5adee83e26d1f77ba3496d250a1ce8669ebdae286 +size 7676528 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..da60ed10e3f50ccfa09894c94607d3c1f63dd2f0 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7285950, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_04.json": { + "num_bytes": 8279218, + "checksum": null + } + }, + "download_size": 8279218, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15565168, + "splits": { + "train": { + "name": "train", + "num_bytes": 7285950, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..f87000eebb159ae80c2b69a3f1c34a37ee9d985a --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "0718d0d5444b29ea", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b7e8741ff2892b104e15eee1f00eec1ffcb60ff4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23200c69a53dc05e03e2f2ecd8af46aa62fa1c56fa0c1d018a716619583d7541 +size 1922192 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f4527ae2419a5e3f990d40df5e0849c061b4def0 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5638f34b582ac949fcdf6795a65ea3463b909720d81a06732147596d8b6ac26a +size 1961056 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..58ca39b22b76b76542b65d470d86d2bea3e43cea --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddde9983ac7d2dac99b5a8ebbc6489d7c1e2b988bb776e06ee2fcfd39aeb96c4 +size 1967392 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0c7fd3846588cd312a7a4bfb192ddb8fbf436b71 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/cache-6c6e3b7f28a2a296_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befe3da270c7b544b4a37ad928d080d28a896ab858fd41b1379819be7b2805eb +size 1894560 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c8a140604f1e5e9bf6c5364892e889de5b29cac3 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be8e96884028f0f7f66a2d5103043ca5f43443664aab668640ef02a54d7bd76 +size 7741288 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4a6592669cf04d687175727a1242a3157f1f9fc --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7351520, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_05.json": { + "num_bytes": 8342040, + "checksum": null + } + }, + "download_size": 8342040, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15693560, + "splits": { + "train": { + "name": "train", + "num_bytes": 7351520, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..87ee4fc1f721a042183269ec89980715df9bb531 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "30d4ff0a718fb02d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2833512515b213f25e8f808858861027b98e2ce6 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deebd7ee9e2904892b22100e94a7d930d0e7ae6b0c1540c039fe06d96c0996bd +size 2003168 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..033081e9f8b121b7aae42c8f96c6050d070277be --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61649a55966dc9edd689f6ac041f7f3b30066b50d07525c7ea8cbd08ed8aa8e7 +size 1932432 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3acf5693acc13ecd28dbc2aa1bfb4d1e7e2e83bc --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622511a0885c86de88df93c138c6f33878d287293cac1ba718f3057d90d107cf +size 2077648 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..052230caabd58d3266b5758dadda4fe1896d8a7e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/cache-c509e5eca59b8b55_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04da17650c5fd9672be487f6a7de32f20a559eecd845a84d68d979b292abb9f5 +size 1968264 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1ee316bf76d16f97c97a098157cc73adf255e684 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9deb5e265f7876583f9b8b1d672e83b31c141d2822aaafc95087774312fd0d20 +size 7977632 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e4d829e34a1aabe81e5ecc49b355c8a6a3840114 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7588693, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_06.json": { + "num_bytes": 8571022, + "checksum": null + } + }, + "download_size": 8571022, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16159715, + "splits": { + "train": { + "name": "train", + "num_bytes": 7588693, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..9bd9a659c1bce2f279c74338334575cd4e1a4a48 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "1eabca2410fd07de", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..dda21b12866f2a2fc7f6f84364391bcc9912bbf7 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdc9f4f72e21dc761192fb422a31b4178d77da4f185a6adcc9aa66bcbfa6e5b +size 1931912 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..95527ed36c30c6ea6ec7676bffecb6f4e9a6f522 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25a409a049da1abf03f4da0a183ac0afc9cd5e1bc973f17d880ab9d74a08bdb0 +size 2037208 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..826b379672e23a27941410f7aabd6c47d5fcc5c0 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7781ad04376739a362eccab1c9c2d5660b7f4f6fe9e510c6689d51780e06af +size 2035584 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..31bba0e3226d7761cc460bc1e415264318b37c62 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/cache-5e493436411cca0a_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8cf534819afc7b8c7e41a732e64a744a72f2d8ddaeebb1dc1e976e33b86ede +size 1979176 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c0c415571109e288c9f31577440b11dce1c82573 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e9e77987a293d256ef9d7cb803b3853e7437f2e004d75c42b7793784b4b715 +size 7979912 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..07000a9a735529ddee3ce91d219dae59261506ee --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7590275, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_07.json": { + "num_bytes": 8581233, + "checksum": null + } + }, + "download_size": 8581233, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16171508, + "splits": { + "train": { + "name": "train", + "num_bytes": 7590275, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..7e9022a1acaad6f25e19675504ab04b25d076e33 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "d4ac6d3f8e131fa7", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b2c2a060060afbf39a3c2703b136c453a0616c6a --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306045b81374dcf69adc38bfc49c1d1f18b874544ebc6f4bbe6a33dd9416b90c +size 1986384 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..93756a00f1bbed2da5a53a54421246b71bff4ce1 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ace247c3fe46023aff77f28d5e56c660d9525c56469e3de347cbc9af73918f2 +size 1947144 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..61d5f99a445b1f3a0cdeb7437f62f00d7b51b390 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22b9cd79102f003a588bbce6623f017315f7601bd87b1156951e27f86b25da7d +size 1981952 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..721187170bd1e8d0ece838c726660e7fe11d9f41 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/cache-755d24a29308d6c1_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b4c772af1d8e09046732c926f652a44b4d4db3f393188fc16e5b965c8b5a93 +size 1966360 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9a9c30ade2b46340a7b16a201eab10512149fc14 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9857f6beee52f2c136980f508acb570d46866b3cc18c63653a19bcc67e4b991c +size 7878016 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..85586e975ae9411d5ea80ea7035380bbc3b37566 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7487777, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_08.json": { + "num_bytes": 8478861, + "checksum": null + } + }, + "download_size": 8478861, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15966638, + "splits": { + "train": { + "name": "train", + "num_bytes": 7487777, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b1f55db75ba2082c79d8c6f8171eccf8cbef6006 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "b5be6f49fe43a12b", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..758b5c9558fd63ca1e7a3ccfb7bcb93ebcb874ef --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b870ecc686c308e1318504850bf40ee7e5d8d0778b030af67179865c78d7194 +size 1981288 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c074ecd3ee512506ad9eb2c324693c4228afe835 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7836183465340a086b47e6cb2494d20ae477e79ba4ad92ef7b7aec674283930d +size 1959216 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..35b7393333806ee8c9af6370fb46834fcceddd31 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805f00e3dbd02847cff55809e8c82f8e6b9bfbc9e4f002bf74a86cede8959840 +size 2045720 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a58c8bcc31c5697e4dd272604ccfa24b5f7b6cdf --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/cache-328e2cf6fbcd0a79_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3454b43d0cbdafef786a5576ca9e43913ed6b0e5bcbd79fc9cc8e4e7e81d814c +size 1949608 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ff3f91f22a3c1a98ccf0c58af231e96840958bc3 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774718cb2a67f6d05bbf2f458e8e0fb3c070e12447f185c6de1f5b9e7b045605 +size 7931944 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5e87277e15cf2bf55a0f54ba7bff9f233d97cd61 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7541773, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_09.json": { + "num_bytes": 8536644, + "checksum": null + } + }, + "download_size": 8536644, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16078417, + "splits": { + "train": { + "name": "train", + "num_bytes": 7541773, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..bdde3ad9505da871ba8762a321bd68601e65fba6 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "aacad84d5e309e7d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e58cf0c198fdc29f33fb4db2c8bf00b2fc8ccadb --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c4e4a90482dbc0f38fb869805c5135e30de097575467587acb09fd7dd30ad2 +size 1999008 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0aaad3a658c63c4a2244a8c1b8bd3f9bd35fefca --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa8ad8128d0ac9dd89de7fd40a837026c95d7abfdf6eddd4c59f1f15b090949 +size 1993568 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d2b7674972d9688189fb2c34a27f25c2f47aefd0 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6917a8efe132b7f57b388db98b9230370202d0ed47f516a741055955f25ba37e +size 2029304 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..73ba2d1e8c8eff265f8291a9d44112ff250eaa95 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/cache-fdd1e50d5b1bd9c1_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d769f33c5984a44053d14b3379360f127946860983ddc048a37b275c363ac7 +size 2055960 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..15edb1d4705e869738ad3ec127628eb335c6d591 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afe6c0fdf1fd5453186fa98a601aac6d2139490c1f68bda26bda4bdcf6b1c155 +size 8073904 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..782f0e4335635fefec72255602260ddc4dce4908 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7684339, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_10.json": { + "num_bytes": 8671454, + "checksum": null + } + }, + "download_size": 8671454, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16355793, + "splits": { + "train": { + "name": "train", + "num_bytes": 7684339, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a07f6e15e1752a8cfe0544f8bae1088fb9f0fb0c --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "92632d0fd4dec098", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2a967afd91bc8ab00515f336449102246c375dcb --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08e3fa0d3a52fc806ffbc08b5f2207ead5e0dc06339cdf7fe85847a779bc4c48 +size 1883848 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6c4a0a4e77da589e981eed3c617af63635c8ac70 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40afb60158f584e7f6d7532ba9116a02606eb234c5223191500202d657381f99 +size 1935760 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ca3bb97cbb9e41dbf670f2066ef49d7b984cbaa8 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddfd3380068b8620754a2274b66b48e235b6ab96ed664ab9ec0bd2fbe703c04b +size 1983272 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..318344174eb1983d8236c5f88e0d82614c5ecb13 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/cache-4e1e60661f892f1f_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574550fb67a61c214ff2e9d593d18196add523a567c6d31db3f0e855fe0a9a99 +size 1987744 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9f296a9d799fc9a8d6af7feb59f6c0ab4b9a7d60 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d423072784394125d659b96ec4a64f84042724f969a7045cd87415c149bbc218 +size 7786696 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..565f5f20807c6a25464f4ec2d6c6ac2423d47d83 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_11.json": { + "num_bytes": 8385641, + "checksum": null + } + }, + "download_size": 8385641, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15782655, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397014, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0cbb44a7b32e8c960e4cdda57d328fe6c07e6f86 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "03b76e1622ad0d25", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..97f869b17527a902f2f5fe4a15586fc2d999b15f --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48641593f38c92982266ca1b8c4e196108762606377750944341a7f9778d46e +size 2018144 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1c11d9023b7f12ebaa61ce8e8ec950003015a8f9 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332464a66013f5ca86444c82d07d0c787648c6e856943676d216089ad2f2d845 +size 1871544 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2cdffd20662a69dc9f787d2edce5827c27043897 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:385ed1b7eb71d66cb430c88f08420adf60001ed028ed45ebf23c92f57eec75fd +size 1979864 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..17cd2645e7cc193215d564715ccd3703d760f6bb --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/cache-3e8e033e065f0584_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef0a1d3c6c8d3774e3f7bbc589660c3efab836937184856fb021f3b19e8fd89 +size 1922776 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2866cf1179f2f3dec6f1da5664c88a8fc2eafe87 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e18862cad54d469514ce1234144d68d5e19eb9e68b89b8a4de8840f6ffac1a +size 7788360 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0cb47f8271e399d38764948ce1b1265fa42f0408 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397632, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_12.json": { + "num_bytes": 8394845, + "checksum": null + } + }, + "download_size": 8394845, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15792477, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397632, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..80777115d9f493cf12332828fd8c44c80356a940 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "e4cb94a95ead908a", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7970dd29a44e21e503c894e9ead1b204098eeb94 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ec2baa9c264d0c8f78c6f0927b19d4bedee69ac2d272dfa20cfafdd5eae3ac1 +size 2000872 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..45dc3344c741374a9b4fcfec00aa598e2f046381 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcc4b4e8c3e2efec054d82178f2efa2ab7c6ab74903abc157474ca4d742053f +size 1894008 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3752657b851a295f20293848a1f9426ce97cbbad --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee858bc8cd6bda5d1917471ba565e5ec51444a505a5f26f438a1f3011b16f48a +size 1934344 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c796828624b8f0d40ed10073fc76a1edbe5abd85 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/cache-a68f893a934c5532_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63c48457055f787bba905852aba825b5de86f92d2ad891ea18aca5d10b7b9a1 +size 1971600 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4b7d1345b39d4bfb1cdce7b358dca616116279bd --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81499632c2a6e5f58b3d3c3918d3c6fdb1f187b00c65020c3ab6903227f4735e +size 7796856 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f78b91818c9ddac7f26fb418556b151338fe132 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7405908, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_13.json": { + "num_bytes": 8404811, + "checksum": null + } + }, + "download_size": 8404811, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15810719, + "splits": { + "train": { + "name": "train", + "num_bytes": 7405908, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c8accd2623e4a7f3bede1cbb2e70100d62c06276 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "348c4557f16bdb2d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0288be61b5c042ef2b01b11007a7fb879aee40d6 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c76ad53676795b09739a657e7616d1215d270df9a8a5fc99d963c6725cbd7bf +size 1960296 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7cc4f5205dd52e46113e65cb3142c900c873d3ed --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104cf5cff6ea043c573d710a9951f567affd3188bc0618425aab79de5bffa2ad +size 2001072 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b0443e81b5c6c2c3fee33490a4ec5b66aaf8b8d7 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4908f4bcd5f4285a1a14e8b5d7e79a84cb96214dd6b7347b7a158a5964b2b9d +size 1959448 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..83ec08ac411cf046bef153e05a3ae7d82a4f7eea --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/cache-064ad2f648d02e6f_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7324df0278c3c4a2695ca24f8178acd9c54b41a9c5465d6549787fed9fef15e0 +size 1999472 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3c18af71b2c09468ec665b897e400f8aeb5d67ec --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e531c68726be1510aa45c965357180bbdc0fab315aa58cd299a4d7d3d590e1d5 +size 7916400 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1f5f31f242c6c70523b2b48d035593617db53e0d --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7526045, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_14.json": { + "num_bytes": 8519986, + "checksum": null + } + }, + "download_size": 8519986, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16046031, + "splits": { + "train": { + "name": "train", + "num_bytes": 7526045, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..9b9f37032c55d1e90fb19faedf439ee65326f318 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "6f7595ef99547964", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..16a9b8354bc8c474b43dc31b7ec59da5ab8ee9e8 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34fc1d51cbea286fe3934b095f6d7d8cf677efefe81d903ff20e930a6fc9e592 +size 2026816 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a48b1119e240ffae291aece26c6fbd8c32b7161f --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87d7957413f5d96465c335d842c49b695963d20b678b4b85f4c8d6e274e420c +size 1925440 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..310e3bca26beea9eb59ce19eadc1cc5e53ce9177 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47507ba315b80b1fc75fa100c83958a32ae94bb59edf5e199022ca364257e76d +size 1906400 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3b79c321c9f750d292aa5a15f5db5644e7c42801 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/cache-e7f0026d9f62bf32_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a2a0be2be08a98a195a7ea450d56dd95ebbeb0e9824d0f42378030db6b6cbcb +size 1990056 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..380289e72d6df2dd4be09389ea5ef3c64dda2262 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5aa4aca0da61cd5f24a14ec1da3b95184ad6906f40b575818dd7b464c33e7d +size 7844816 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..675c725ffcab63a63c7f6040add40f629c6302f4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7455328, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_15.json": { + "num_bytes": 8440301, + "checksum": null + } + }, + "download_size": 8440301, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15895629, + "splits": { + "train": { + "name": "train", + "num_bytes": 7455328, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..313ffd0ba43c1bec21d2868c20b699686a7fb0f5 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "8480e9f0de1732f7", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4116091bb5fd592cdba0c94592491a3a8786362f --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d152a333e3f9576f082479a79678dc62d39f9ac4d1ac9276b0138a77d7372398 +size 2003056 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bc20a76f17db23994312673efb33e777c3e06c92 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1c2700a77db7cbd5758ffc98eaad6be92560de1025d8cfdd3e3ae8bf32337c0 +size 1902352 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9b57baf6a6d74aef365eebdda31df0389a81c6b7 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716d6c997ab6fad21609ae2a258f2d04d9aab4f418a6ff145535bfb01959ff7d +size 2007232 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5a47615f38d970bf082cd8b9ca7d869d27b318f4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/cache-c8618e708a1125d8_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112cfc4607f9d794acea568074e21162f62a208e99f517b0e183281550afeec8 +size 1994296 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a36c7d363523ada78b70652c5a0b7c8f6fa941bd --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efcf62c93657e6dba8ffd1cb86f35f1b36788f34eb1647984bb32d995a1f260 +size 7902976 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b0f5212e00804091a41e20f5b4a1681e679ecc --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7514211, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_16.json": { + "num_bytes": 8497254, + "checksum": null + } + }, + "download_size": 8497254, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16011465, + "splits": { + "train": { + "name": "train", + "num_bytes": 7514211, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..59d2d33cb077ad7cd46fcd229b7584d5a1a2a75b --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "97334bf3a54d1f87", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9f5be5436b24033f3c8fcd3307e66277bce716a5 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d25918688968b9b6c7af28a903c9cd9e25d6f6f16af9a18cb4bafa959bc7012e +size 2027024 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..38b381a8d80e70f380e0c1be1137d009784dd10f --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17639cdc787db7ebc13afb22903863fd682f3e2c33683e09edd4b6fd5425f82d +size 1878128 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..edbd4959650883c5fc2e1d1863157d7febcb5bb4 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e0862dd0b24815f40f2eca0ade5d37348dcfc81a471bcb264021996125cb4a +size 1877016 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a944e26ca7851c5ac276f070ddb95fc126eab10a --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/cache-f1f82ccaa2d669b7_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cd816d0ad8e6a5051007bcca6663a0a289dee011ca9d762d1c46eb53e9e9f4 +size 1955048 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..41258a483e954263b2cbf4f274b1f456280b0219 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd542e181fd7e9e98984baceea1b5350ca8861e53be362461f5c587fb5bbf8f +size 7733216 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a8862d6bc73fa2e77d2f630e5d6a883d312222 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7342615, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_17.json": { + "num_bytes": 8337621, + "checksum": null + } + }, + "download_size": 8337621, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15680236, + "splits": { + "train": { + "name": "train", + "num_bytes": 7342615, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0e2d53602df681e3fb327415cc92959f31b2a225 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "bf7bfb80feeaa0bc", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..24531f7bf761676041916fc5020af6ae28559800 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e0105b33c5e6b730a827290211e8df0b0c21defb1d5a116882a400af7c689e +size 2019904 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5e4765258eea85c530ac8fa1b6b3aa526359d795 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0930e8bbf45b5c2bc991b59f7d41123e75e1c5fe3f0e01af167e8df9328ba6d8 +size 2012016 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0b1de9a2a3224152022ee9b4cf3a97f3488da4ac --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615ee15ed1fe0ee8aec3cf6e188af105bbec0af65af4f8fa1dedffc1af2705b5 +size 1932408 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ce802923cecf3e177f7f798f8b458d3ab03d740d --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/cache-3ec0fee7f2f41507_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a5cc6316f14daa44a1fc13cbd21df450081a224cac495b76a839f36821f289 +size 1988888 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..87b63f376317c5491f8f394feece206b9c1e480e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df87e2dd98b46ae9e704d64dcd8be6a652747275612671722e3804f0b89c6cd0 +size 7949272 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb216f3b809932dbb778e54c17010ffdd06444e --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7559827, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_18.json": { + "num_bytes": 8548766, + "checksum": null + } + }, + "download_size": 8548766, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16108593, + "splits": { + "train": { + "name": "train", + "num_bytes": 7559827, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..f36543d805b73770297e6726a3eaa2f415d22d1c --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "dc482946b96e1306", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00000_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d8233d26afe6241245f21de68c1fd628830da7a7 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37717a4954161b1a8a891d704ad6ad3837bdf4f303365dceeaba783ea01e2655 +size 1909088 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00001_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..285e6745754659b025cda314f6f349bd3fa6b1b8 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:287ed6ed415281e016026578b5573ab8a7dc4018996523931e13d5d37670600e +size 1892576 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00002_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bf0673812a55f23194e5446690b799f8f9fd2948 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39e2350f9f338e9bdcfb0f9aea07bcfc824f872a364301be72ba5bb76ad92d70 +size 2012760 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00003_of_00004.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3121a3b7d71b2fce30d96076990490299dfcfd8b --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/cache-4cfbea3b61a99c53_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99dfe4af9e1a5c88fd8f411cac1b591652744f5cd129e9530fccf1662eb00a23 +size 2019728 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..241e367a03b7729001e793939518e9d0c86931c5 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:522eba37d4750dc821e6303fc55036d7bed61e491a7423e6892ffa6325db1bac +size 7830288 diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/dataset_info.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..51324591261cbedeaab4bf3cae73c0469c97e026 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7441014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_19.json": { + "num_bytes": 8427096, + "checksum": null + } + }, + "download_size": 8427096, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15868110, + "splits": { + "train": { + "name": "train", + "num_bytes": 7441014, + "num_examples": 5676, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/state.json b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..d27c6c0918c39fc1ff4e0a6a094fd5c1e60fbd55 --- /dev/null +++ b/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "7f48e74ea20d31fe", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_15pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_15pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2530d7920abf1b9c5a5f19366152c15e214df9e3 --- /dev/null +++ b/vmllm_cached/siglip2/video_15pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a737543d7657ebf205436d07eb7d2c8f13d910fa6ad6229e5c23b314c445cd +size 235365888 diff --git a/vmllm_cached/siglip2/video_15pct/train/dataset_info.json b/vmllm_cached/siglip2/video_15pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..d7458e0c719fd4f6aac47817c0edba2f2a07b096 --- /dev/null +++ b/vmllm_cached/siglip2/video_15pct/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 229832385, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_small_15pct_sharegpt.json": { + "num_bytes": 259557276, + "checksum": null + } + }, + "download_size": 259557276, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 489389661, + "splits": { + "train": { + "name": "train", + "num_bytes": 229832385, + "num_examples": 170331, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_15pct/train/state.json b/vmllm_cached/siglip2/video_15pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..1dacac19d3895f48dc40bcf7de9eb2414e7d5add --- /dev/null +++ b/vmllm_cached/siglip2/video_15pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "d2f2ce4388c9fd7d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_20pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2/video_20pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9e8adc0fffa5a1ae2c93befd395241b31aab9c1f --- /dev/null +++ b/vmllm_cached/siglip2/video_20pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b0902b9b5dea453d87b7e00d29ef95cc0f075d375fd718448b0c3e823ac2cff +size 303070760 diff --git a/vmllm_cached/siglip2/video_20pct/train/dataset_info.json b/vmllm_cached/siglip2/video_20pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6a57e54bb67371e1eecbc2bcdd57468aa252c35a --- /dev/null +++ b/vmllm_cached/siglip2/video_20pct/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 295925654, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_small_20pct_sharegpt.json": { + "num_bytes": 334309604, + "checksum": null + } + }, + "download_size": 334309604, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 630235258, + "splits": { + "train": { + "name": "train", + "num_bytes": 295925654, + "num_examples": 220038, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_20pct/train/state.json b/vmllm_cached/siglip2/video_20pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..7b56ed0370fc74394845ad72033543919866988d --- /dev/null +++ b/vmllm_cached/siglip2/video_20pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "2322784b3b41ec4d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_full/train/data-00000-of-00003.arrow b/vmllm_cached/siglip2/video_full/train/data-00000-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ed757c68d46316934b67a40b3da615375c8b0d12 --- /dev/null +++ b/vmllm_cached/siglip2/video_full/train/data-00000-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57a321c51386efbd32f69ff684a09451021776a82066ad3444a5c4ab1ee2716b +size 354565576 diff --git a/vmllm_cached/siglip2/video_full/train/data-00001-of-00003.arrow b/vmllm_cached/siglip2/video_full/train/data-00001-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c4759d9f15fdc89352dc7be8a5148c71b7ee270f --- /dev/null +++ b/vmllm_cached/siglip2/video_full/train/data-00001-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f838ad42bfc79f5f41015510cf0065bc68030606294d0feb687e99a89afd7599 +size 354296560 diff --git a/vmllm_cached/siglip2/video_full/train/data-00002-of-00003.arrow b/vmllm_cached/siglip2/video_full/train/data-00002-of-00003.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0628b11c54098f8920aea14d17070103038c296f --- /dev/null +++ b/vmllm_cached/siglip2/video_full/train/data-00002-of-00003.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854af85c0b546a3ea4953c6439cddbb81f88c2dfaa58ace566ce0f1eebcdc8fb +size 354842288 diff --git a/vmllm_cached/siglip2/video_full/train/dataset_info.json b/vmllm_cached/siglip2/video_full/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7016ae1315aa291acef19464b150544de3803b99 --- /dev/null +++ b/vmllm_cached/siglip2/video_full/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 1037696374, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_full_v800k_sharegpt.json": { + "num_bytes": 1177312903, + "checksum": null + } + }, + "download_size": 1177312903, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 2215009277, + "splits": { + "train": { + "name": "train", + "num_bytes": 1037696374, + "num_examples": 800001, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2/video_full/train/state.json b/vmllm_cached/siglip2/video_full/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..3861c43206e34c84082e7ef6932e1f7b47617544 --- /dev/null +++ b/vmllm_cached/siglip2/video_full/train/state.json @@ -0,0 +1,19 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00003.arrow" + }, + { + "filename": "data-00001-of-00003.arrow" + }, + { + "filename": "data-00002-of-00003.arrow" + } + ], + "_fingerprint": "2ec141a06bbdb5f7", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00000_of_00002.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00000_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..475bfc0862a8d3f3ccd2b68b83a5d51e033335aa --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00000_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cef4415f8b57f630f7159389f4f82963c460766f06a85929c6c13e75c1b07d44 +size 4128 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00001_of_00002.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00001_of_00002.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a44ceb1f0847c49aef7703a660270f7e07a0008e --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-42be3eb8cdb299c3_00001_of_00002.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1722c4b924f286d26bfc4c6c6959cfadb7703e3cf536877df42f13393c91becc +size 2280 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00000_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00000_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7b92cb507dbe63f69b98699d00a4f20448dac0e2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00000_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1681722c7322330b418989dab7f302a43cd77082f11921b2995be5999a96e0 +size 4348624 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00001_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00001_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b8a7000fa9ccbf96545c03d9b87a76591ecf877c --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00001_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8adf8505cf61251155e273f8c54f6c1da814f78663b1e3c2b89fe1b2a8f027 +size 4397128 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00002_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00002_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..30888fcffcf663c3f8d56f73c2be287881c9ce08 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00002_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174569056ad20df3644e6c773eff0015dc014c825585a6cd06e55f192fe00a63 +size 4337304 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00003_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00003_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2dd82c5ee3efa1cd23395482716def4f4c6beaa8 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00003_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4167cafd9319f02f660e17a347fcc86c346d398bb87ad4beabb9db306ba4a831 +size 4294744 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00004_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00004_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..eac2fdbd8329954dc6c335faa8993f0799eb9323 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00004_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60c718ec6ea3ecf11d5d102a7b894a227d46485fce66956cc11c8b211fb210d +size 4317096 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00005_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00005_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f25577a682a6d3023bc59e1ce0ea165a117e0651 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00005_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22f1821214e4e9d15f8903b343ec9c0597a1fa3309148c313bd99ab0ed0f1816 +size 4366920 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00006_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00006_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ef68d637878a907efe1c45e79a14cebeb296c886 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00006_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a9602db103c579248fc88d3e5ba1200ae2f99ccc6fb788b7d2b19d76e82f8d +size 4356176 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00007_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00007_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3bd7e09f7710a949ac2d2e003d4997cf9e8308c4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00007_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b624a4a55127bb5a41b3b1087c62af23f0cccadd4395d772138a78ac8bf000e +size 4407040 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00008_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00008_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..fe63f7cadad1dca0a56918a645fbc06cfc296f92 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00008_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ef97485337f6a8e03317693a59c71d7159eaf96c338c8d2fc91e0b2de02dfd8 +size 4347048 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00009_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00009_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..eada9c1b8585a9755143fde0ed65e8fec54be68a --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00009_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cacb0bcb65d8804fa509e0c2b5b61fe6daa534da6592c1051e8855a853bf004f +size 4314704 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00010_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00010_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d545a0668fb0d232f1e5410612d85f0ba7908fd4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00010_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6827a18bc8aa153723034da72053c2e12fae0852a0a22ec09582a1a3db0012cd +size 4371096 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00011_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00011_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0873473bf0de7bbe8cbe0eee0c0d7c92da16b062 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00011_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec121e78ce26a87e4a3491d336355a53d6de7b4712792a8bde46e8146e94e73f +size 4369816 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00012_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00012_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a059804f94f46e20c85cb8530b0a7964ef2a5981 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00012_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce718572b801a11b635e804febd741a2f9e498f7e5d8db337c9b0ff835a9617 +size 4378360 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00013_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00013_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..eefba60dcc46386c0baae7821c6f50968b3dd014 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00013_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54def4880b66cbe24c60dd9bd1d4bf610515037c073d7be886db4361c99be269 +size 4362504 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00014_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00014_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d1d095d3301000582b50dcccb0dbb52c9a325843 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00014_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c7d8b2ea89b723c38ae89517b35662ce0046a50a70368c7eb3dd7c11b32639f +size 4452368 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00015_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00015_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c9503f2d585ebbb35d96f28695dccc6097c6c774 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-6ff0cb43d943bef1_00015_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f638e9fec95bf7b92063071b844327c5fae83476c1b991218c7c835e2ad21e9b +size 4372144 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00000_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00000_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6ae905df968e21826f1d7b40ce5a546a48aaaeb6 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00000_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b292ffac24383124dfd7b00887df0e2d506c2119f1f1c9cb779f1cdd16ff7d0d +size 4348624 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00001_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00001_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2e70ea1e05770ef281d845d50281bdca4f12dd5c --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00001_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:913fa7fb758d2d30e9a7fe4c68f9aad245fb2818108d8120557b2b4d90567cf7 +size 4397128 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00002_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00002_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..63aaf1d177d441361e3cf70fd6c697236f30d19b --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00002_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a352bd6b6bf101dc73f9487007b76e45b44d38a6bb71f89670313a81fa7381 +size 4337304 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00003_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00003_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..706e65e295d6bbdff6f73aa26ca76f9b683f99a9 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00003_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e07f58dfcea20278e70073bfcc385bf64cfbfe3af31d3a85dad7c68a9311c58 +size 4294744 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00004_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00004_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..45755a8a659c7c90b40ff7172ff64fb04d949eb7 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00004_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0bbd5d881161b35e4fd3703a4c7147d53c6a17211093e74b863e418d3d7e74 +size 4317096 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00005_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00005_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..61f577c317d32b21702afefd5c07dce628ec1a85 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00005_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4886d98202b39668289ae496579f4a6073ac6c2dc839b65b28c8231da0cb4a +size 4366920 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00006_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00006_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0c123040f28abe1aec3296799ed1e16d84a1ec21 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00006_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32c67bd8a33e13aa3b30214668acc0d5861260a96a064231360501870bb9b03 +size 4356176 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00007_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00007_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..cfc3b8530bb60469fe5e59875489ed68d83594c5 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00007_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2382895ac7144598cca8a81017e5f3d0d387c82ce8395b3c8312ff1a3af76577 +size 4407040 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00008_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00008_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5a4fa0e90f01a3eba08633d677f2c5396658b667 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00008_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96219d38c12ca220b8d4c89714fa4742b88efbce814c8ce991104f59efc21649 +size 4347048 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00009_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00009_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0e35e46b5fe94d9a9d608a22e254721780cf7072 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00009_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24490de7ea44c3f177c062b67fa75718ab5df73d183e04d697bb5f9f39cd010 +size 4314704 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00010_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00010_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..80bcfd372c087a62b7050c8ed519934bfe5b0f0c --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00010_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0e48fee95f2802fcb1959cbe5c3deeeca63a3540b0eb93946f2a3753964a37 +size 4371096 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00011_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00011_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b4cd95bdba8e46fa980f2d60d32472115634591f --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00011_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02093f91254b842be02e96b7ac74cf1773a3c313c2e37725731dacd982c9d664 +size 4369816 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00012_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00012_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..cc34f8e67c26e110b28cbca60f53a08ba6010d25 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00012_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfe62590457264f7dfb570748e1559db60192ea0c8910327dd10fbf7eb8fec9 +size 4378360 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00013_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00013_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..224e5e3f1d55662eda97b8363b41813b7f79d733 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00013_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec71dcf3932db2051c03366260cef13008da9cefbb9514ae24a38698b8f811cf +size 4362504 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00014_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00014_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..385c371eacbda01bf6db9a9d2bf4e9dcc62f09ce --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00014_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c4ffc4e866b21e5fc77b6a0279e10aaa0a9899a84061825fdb717f2af17cb0 +size 4452368 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00015_of_00016.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00015_of_00016.arrow new file mode 100644 index 0000000000000000000000000000000000000000..fdc4ce2d2f77ef896acad1701afc82279652e710 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/cache-d5d2d39cf618873c_00015_of_00016.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4848f6fb91d760b8faed6e7fd5887982b6f2ad0a704a2304014f6fa602dc425a +size 4372144 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7a66627c527851e655a096b37b0ac6e08430ddb3 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc1a76a5b188280da7202545abb45dc5a1203a22ccb8b8089d695a26852af13d +size 69352320 diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/dataset_info.json b/vmllm_cached/siglip2_v3/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/state.json b/vmllm_cached/siglip2_v3/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c309d469696ab6665c60e911383968e9e157766c --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "2b2dbbebf1aceb79", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/image_10pct/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/image_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..d229e7267fef292d162fe950fa6606b9b1462664 --- /dev/null +++ b/vmllm_cached/siglip2_v3/image_10pct/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "image", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": null, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/image_10pct/train", + "rows": 73859, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c7352dc301296ec516a159f4a7060093999e160c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c48a2842ade3b5232bdeb14e50c58d59197e8594400110afe12ff6b5ea0aaba5 +size 1946512 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e60111eb394e4213be218b0500716bc525648c4c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b430aa31cc347e414149d29c96abf19292a0c652a2ac99510f6760501230ded +size 1967768 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..92ebb331afc73bc325a84559062885fa850a9b6b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e827858b6e484fc0a5652036355172cda0130f7f37ef1c3d40f62f409fe5c8d +size 1952400 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4b85535bc1e862fdfa593a52452ac63150333975 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-b08da3e4958b57bb_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be2829c1bfffe8edd3ae10e54170708094a94eb12af1fa984521044a3e589c81 +size 1975104 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..83b0e08a3c419edc21d70002fe7f93dffb4aa2c0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358c39eb7b036232b06d9fa3d39a352de91badc927bf632c066bef0a1364d7f2 +size 1946512 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..42a0339b363348ecb4152422b566eb243dda0300 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d28aa1951f7f734d3dbcb4900f385959133524c08bbd2478eb0176e7cebf589 +size 1967768 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7d7fd3f46c9af101d8ff42386dbd4304b36f5e30 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa165ed2bbfb29a1bccf01e5235cfcbf82b7e85ea2a277101276fd35fe155473 +size 1952400 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e910ef591a0ea4630244c5d39bd8ea5980861677 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/cache-bfb8f4d93fae3d86_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64ff51137f7c60277211d88103c7ce51bd6023dd3b26496458746c45b20aa086 +size 1975104 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..445ef8feecc48f720badbdaff0fa05cdc3c8bc2c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c112707d5ca6b943a742539dec884d468d0637d33c0f64a9254e298476515183 +size 7837872 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b59fb25a630e78cdaca99936940baa155b04ec05 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7447721, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_00.json": { + "num_bytes": 8441128, + "checksum": null + } + }, + "download_size": 8441128, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15888849, + "splits": { + "train": { + "name": "train", + "num_bytes": 7447721, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..f4ba24627a0ded5e03e575adc0169557a9e8b5c0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "fcbefda1c6f39fdf", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..000c2e074bec0831a91b07e026a0dee835297eea --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ab81c5e1aa5514367972c203d3ccc3b9a0de7ee8 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c17cb7d87a94e61f20d75c3c40d79b6844f559b249b6bce81cecc2e892558c3 +size 1938368 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c076773b73fc944f1457c267b5415e5de749c8a3 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bdd838e6ad373a129420bcbbb59fad6da589b0ea90e22f86082660fa73f324 +size 1933560 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bc13126b84117ad10a0463b467aadbb4aad885d2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd836903c4bc02b4a434bd2dcfda011179f216b05765b674ee98de69ee89e44a +size 1979440 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..aecd558e36bda42ce4939ceab833627f3b0d37aa --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/cache-87b300b8672a317f_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f77b3de5e8e96a41d9f56b6eeb2c3f951dd8385c487980fd4a634d73dd9692 +size 1912880 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4b2577ad9674c4425f39dc4f85f4655ce37dfbaf --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5495452c46a0b7877cf62597e5101f6595304bba0f1a6a509b5ac9c4b798027 +size 7760272 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..9753431187f753de6088f363a3c32dc44a55eac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7368826, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_01.json": { + "num_bytes": 8374839, + "checksum": null + } + }, + "download_size": 8374839, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15743665, + "splits": { + "train": { + "name": "train", + "num_bytes": 7368826, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..94466a607406cdf3565e6ec644f8975485ae9689 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "a52ede1910efd117", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..880d1c2aa8d225c6342be31c21377f205760c588 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..44d58772d27e2ee68d768094ddaf1191d63f97c3 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4b03f118e335745209d6de6ada7c413304a539776a86846d329cff069f2d49 +size 1912344 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d8bae480a1d59e69db97f2ccb0bdf499d29613c5 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b3188a7288afb3c8a4a2f0ccd60095fb37f9ac3ec3ec65934df6b1cb2072af +size 1993944 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..620d4cf6cb4f5d91f35f3699aab3115a66792fdb --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae3fa8a9c0344c9ec40482dea53df876f3fd3afa40b85a4b1fec40cddc08d70 +size 1974928 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..29e85d1256fb614e9f6d33f6d8c41e93e4f61a20 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/cache-660215006af14abb_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67670ae58cd63d11dbbfc63c7b0135a60dba3127c8e542362fe1d8395e211549 +size 1976216 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..03d9458b9ab56253b337ebb2db387895624ab01a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a6230e8717317784e6c7516bb9c83f6d7112c19cb46630d67c0233ec579070 +size 7853432 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6f954de72e7e74d0f41e01d288d7974880fca499 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7463924, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_02.json": { + "num_bytes": 8451092, + "checksum": null + } + }, + "download_size": 8451092, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15915016, + "splits": { + "train": { + "name": "train", + "num_bytes": 7463924, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e35b3b377c82f06ba37e3df4320d367020336dcd --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "31ec45621acf1bed", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..14fa6e930d1f9e7d4b216b25c0d5804157b28344 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b51ecc6547eef0484995297e779931ff2a7085b9 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3d15ddda486fb1b30fa74fc53b3114395df682e25df6bc2bbac7c7ff450658 +size 1977200 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2a57498b1ab6f11eb76aaac84c0d6f1b6e4ea3cd --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5fd83d81197b30afd91418732bdce1be80b562830ea3ce67484d16b51388c0 +size 1999168 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..82d9ece00521fef39c456ffccd9bf7fa3348db5a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ecbd83583cde55ea593a6eee4d31a72c7f82b150716ebf9f0e129508a9280e3 +size 1961672 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..832ab9cde20b435ae90b85a349c57a603d087ac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/cache-7b06f8393f6ce5f5_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0ca9184719dfbe8415eb8ef8fedc4c9e3dbd2906a2411ff5be15c545cd28c4e +size 2000016 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a28ad45e4738024aff5281123a19dbe7ddd86afe --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36394d4a8e4ea9f7d6c07c59e0d9128812920686f541fdbfba4b09396fc1fc4c +size 7934096 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7857d783c3661746d540b0aefc631a9bf2e0598b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7544302, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_03.json": { + "num_bytes": 8531728, + "checksum": null + } + }, + "download_size": 8531728, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16076030, + "splits": { + "train": { + "name": "train", + "num_bytes": 7544302, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..77c6c0d6f6cc7cbf3c0a30eff3acfb84daefe943 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "0ce981fc8ef9745d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..85c36553264f59fa9c6b1a12d7617d374a37c920 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..beb5483b098ab8cf2866aa8b5b681a0d1fcb5e84 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96cadbe0cd5ff9c85977cd5bbb400c143915a01dbde17d99dab9a1ad22555f3 +size 1931320 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1124675273cfaaa2d55d424c2a5c66e99c28900f --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cef271aa57dc30277472f54c892bd85d626d7e337ede7824525002b6b8eb7004 +size 1932656 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..411a1b19fb933c9f301f943c9ef72d6a16c05118 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e45ef25d019957bcc5eecd4b10b72bb81aeb821e60ec85d7a5f70fd24416a4 +size 1873072 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..851603f1039b7f2b6f9847660f656b9b80d2c416 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/cache-4275f7db5d41c171_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d05f68d459ddcfbf2a28e955c4481b307a0c065d110c7b59ef1430f86c7a6f1 +size 1943496 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6da290942f6482d3f275b931cb43839d5f59231b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47340366b6d62b3a2227add063b3d8b5b9acb7bb729b43b6c0b34349920f83a +size 7676528 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..da60ed10e3f50ccfa09894c94607d3c1f63dd2f0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7285950, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_04.json": { + "num_bytes": 8279218, + "checksum": null + } + }, + "download_size": 8279218, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15565168, + "splits": { + "train": { + "name": "train", + "num_bytes": 7285950, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..ceade15cff3ee899899f0a2f23e5639a30ad7a35 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "a01c95013bb3b632", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..8def0e6654895b6c7c6350eda0ad4eddbe1e0f11 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bfff7ace48d49cf0586408d799555fd4feb455de --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1161ae414f2973c3bfe40d9fe484e6df36741a9e2689d028548d256a48b2d0ef +size 1922192 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..185264ea1799ca505397dfe7b0864cc17ee20746 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422adf79c742b5f5eb676f974b0d49604b4b60280f50fa2c34a65c5de00fc009 +size 1961056 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c679943acb5968072d6b76deb24fccbc3750cc30 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f1bfc3d01f8c73ec9861ec096966832b6a723a6b0ed58b67be867c24997359 +size 1967392 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..511ba69d95cc59587af1e02bfb8d77c4f0df4f6d --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/cache-f74ae81c7c54a12d_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f507bbfd8d01af3af0adf3a924d9965f2f45993b375a7613e328458e9ddedb +size 1894560 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6213cd56d9f4f213a3391bbe584b1d43eeacf29b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d3d725022b26b8a119b36aa95f5d4f5432654d2e80df569b6be251d6fe01d8c +size 7741288 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4a6592669cf04d687175727a1242a3157f1f9fc --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7351520, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_05.json": { + "num_bytes": 8342040, + "checksum": null + } + }, + "download_size": 8342040, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15693560, + "splits": { + "train": { + "name": "train", + "num_bytes": 7351520, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..da1439637768b8b8b0265b37378721742bf2f485 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "6c6e3b7f28a2a296", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..8a2b34ca7f73e2958aaec881f6d5da21c35dad81 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b859888f927a12c5576d6d2fc9536248ec6d7802 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54db3c0b871d619961b9f3cb5d16803fb891e179fcebb83c42305219326365a9 +size 2003168 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b4aa8ed7b107171b260e48840644ce5563c6ca90 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7852c756e40b10b56163e9009f7b28fdeb32e9f8055490474efe1b5eece4d2f1 +size 1932432 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..be103e2e16f198a9715cecd5a2f7cb2ba18c9959 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc0e110fe1189adbe2e9ba00e2e6f90b31dd9270db623e88f49806f15b6c5540 +size 2077648 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2f663b443fb29f285e7846ef3e1425fc4fda9501 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/cache-adcbbdd4a2f61d28_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31c07bfc67bad37ca8db0da6b5140bbb06591f046858d7959dbc80c6908997f9 +size 1968264 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..50e30a31a831bfe776cb85539eaa11341dad8426 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7cacc66f2ecd2aed95e395fb7c2670472b504bb27b1938e2b5dc3e0457d7dec +size 7977632 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e4d829e34a1aabe81e5ecc49b355c8a6a3840114 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7588693, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_06.json": { + "num_bytes": 8571022, + "checksum": null + } + }, + "download_size": 8571022, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16159715, + "splits": { + "train": { + "name": "train", + "num_bytes": 7588693, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5c506756c1ab32ef05bc95668147296fb84bb57b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "c509e5eca59b8b55", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..c24c4c2b4467055e3766de05ec7fc29bd95a3a1a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..be19a345df975caf9f9aec7b01c914bf9671659b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314965a521368a96d738dce0555911e73913c9537676d17c83e093c33601df64 +size 1931912 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c0bbd7259fba2c98cd4e0d1550e03adf1c344279 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b2973b18890890a2995be4bd083a26576ab00aeff425e788d96c527472ba02 +size 2037208 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b5f17330bfe26f63b0aab7026b98c9f51cad3e3a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7e1004e144c8e9412f1d02b27ed9a051d4b311df93d574311d9b9122321698 +size 2035584 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ea96ce17c53890f59f375cd6b15ebcb96ea5c7f8 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/cache-06dfe0d5bf1f7ef3_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04a6ac3731a380c39780cc2f540dc607068cc165cb2bc23ec7fb8714da4eece +size 1979176 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..56d2e87663cc8731fe8392a58bfa7d6bac4dfc16 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d3bc6954e73da32654572bcf6bbf3dadbe40a033f6f0ee46e04ec451a62e1d +size 7979912 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..07000a9a735529ddee3ce91d219dae59261506ee --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7590275, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_07.json": { + "num_bytes": 8581233, + "checksum": null + } + }, + "download_size": 8581233, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16171508, + "splits": { + "train": { + "name": "train", + "num_bytes": 7590275, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..923c7818eb7e55e0b2aa08ce070488b5c4b35585 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "5e493436411cca0a", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..a92cf5b64296599120077abdf09775f71715be1c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6f7934414ae53d5d227ce7d9193b41e183848408 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a61edd7ff937c9450c8f3aa415abfee97326e31d256d7505b540f6f3d12798 +size 1986384 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e4380ab959b056e69c0379d2eede28f73d739b11 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5bfc8bbea4a75989721c98c3a0fd2395c448b471dd82ec39a72fd2c293a81ef +size 1947144 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..47497b9ce47cee7f81d7b409fd2502fd6119877c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41f5e4254fa9d40ff411dbc9649e9d87b8b374f354a631b849796aa4ecc92d3 +size 1981952 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6db1bfc4be363de3d0105961c3c19db873f98be4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/cache-45033e091ccb2a1e_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a4df6caeab0f4b61e3391267c17ff3267a89f21ecd584f9c9296474589753c +size 1966360 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..41da21b4eaf6464fbbf909ade617ec7ac2ebcee4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9584aab9c44ee0a8bf441ddc7941697415f92729446542e477d440bdac79b1ad +size 7878016 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..85586e975ae9411d5ea80ea7035380bbc3b37566 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7487777, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_08.json": { + "num_bytes": 8478861, + "checksum": null + } + }, + "download_size": 8478861, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15966638, + "splits": { + "train": { + "name": "train", + "num_bytes": 7487777, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c28617a47fdeaf48196236072b903a6e50db416e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "755d24a29308d6c1", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ee23fc87972488e6480845985fbfa9e7f2417c1c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..fd4db6c179c03bb029a9c9891e621076ef20bf0b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c117ba8e7d51afd32f7f3114f984df5ac1887c58effa2a624088fabf99e69af +size 1981288 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8e826e4ab890ff51a0efcd5d870970a8bf6bc898 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66aed79d1a8dd2b7fa4a3f8a58275a94361a49f3f4f0f92fca09c3dbd085d331 +size 1959216 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..65d9f3f8a836a5829c359a238bd669521162aa92 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e16acc42430c5acadcb9a3514bd8d13b41d9663704d05f5d969022608214daf7 +size 2045720 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7650239401650fc24e3a8a4102c154be73b572d0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/cache-9c01ae07970c312a_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b4c59c2186cdfadf219cb888a86b010df02531c34d4fa02af9a315f47b2fd2 +size 1949608 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c1aa64bbaf4c58e8e3f51d2f6c7a5dd1f1b05c34 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b65d8b4bd650099c1fc3ec73d4eb76bee28fae0f1386b7ee0132405116aca9 +size 7931944 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5e87277e15cf2bf55a0f54ba7bff9f233d97cd61 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7541773, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_09.json": { + "num_bytes": 8536644, + "checksum": null + } + }, + "download_size": 8536644, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16078417, + "splits": { + "train": { + "name": "train", + "num_bytes": 7541773, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..195ec6e204f54e38d79321d421b1cb4d1b1365e9 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "328e2cf6fbcd0a79", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..d4dabbaeb2f4358cd44297b97c0d0a24fce20e3c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..88d72de4828122191efec507baa9e680f274546d --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f579bb674f710a307343c283afa12918034a32b594b3bfbaa1e35423223bb6b7 +size 1999008 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..543c918c342a97a1008e16f7d143be4fb8cb0700 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b18ac3c66fde7e0a4d8812256a020a68c31ef4ab2c2882259febba62c9564a4 +size 1993568 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4d1a27a9333d7ed85041855d50e5349e08bf3619 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397054017df697a8c4b978d9a276cba4650ce93908b9cce37efb12a8c8f0ae3b +size 2029304 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ae48a0d5f445d2115a48210600555fef1a55eefb --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/cache-2a6f3d7083990efc_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7114be1c9f205344028dcd22cb25a89bfaa18e46577638b61258d1a3a27050ed +size 2055960 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7b8b08a82ff6a3abed07a00ef862d1baa17cab88 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5940db96ae01fca41203090ebb7dacd3df4698cbde347669505d0aaffcc7739 +size 8073904 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..782f0e4335635fefec72255602260ddc4dce4908 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7684339, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_10.json": { + "num_bytes": 8671454, + "checksum": null + } + }, + "download_size": 8671454, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16355793, + "splits": { + "train": { + "name": "train", + "num_bytes": 7684339, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..015106f5286ab98a885034461146ddcce7a203c1 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "fdd1e50d5b1bd9c1", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..cc4e689f3d600bfb5300ff0e59b1e12edee57283 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b12a75b06cf71a1792839af5cc5781920004fa40 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c7ac79c0a89e838c2da90a615e389e5633819a3f02d8c035a136fffb318b10 +size 1883848 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..4943587d2cdd97fe5d9d62bdb2c27ae85b9bc384 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea1186e11e19b03ec9e0e33f0ee06ba93b1968ecc224094e8b396d6385dc4d2b +size 1935760 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..71916e93393bccd3eaeec751249642b6e548cd40 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3aef7036681e7f7553941d6974de2fc653f795cf7e34c414dc51211b3dc474 +size 1983272 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..dc2f374d98954bde6025b01afc101468026ed880 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/cache-dc954caf860a1c23_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7355c8373f04e91d8da79c568448923991eae62c05d840fea6c4c308b66a20b1 +size 1987744 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9a487662edf9f2b35c3deaa4b4a88dbaf807232a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5923db5318601fa46b52c64571ac75c9235082b119d2bfb465c56045ef74804d +size 7786696 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..565f5f20807c6a25464f4ec2d6c6ac2423d47d83 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_11.json": { + "num_bytes": 8385641, + "checksum": null + } + }, + "download_size": 8385641, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15782655, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397014, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..f43919d21ab9589a809fdc504c5ce8e22e39141a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "4e1e60661f892f1f", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..88ccfccb760b2587799b641b1b0756788481f1a9 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3b2a639aaed615045a96564307a719fec9cd067c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e322e2365a5fd1e9b4a326812e49c249d3ea14ec27315a05dec47b3a0b782c7 +size 2018144 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..77f10ccdd2b8393031fafb57a614e60b908ea07e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1e419ffc90deb367fdfc70062e06d2d2db468b0c3925c8d0b8dacd5cf4ae60 +size 1871544 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5f2b281c4848e07ec6130b52f9bb296314b529cc --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d27f14c847394908a770792da5a560b12344c39ed4f43bd728ae94667a2d503 +size 1979864 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..451e56f37cb9b2042b09ec6d1861e8c740a48a5a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/cache-d89c123a1286c7d3_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebe95d616caf1969bc822f0dbe035f48e10e701a630a561b456829af15d9fd94 +size 1922776 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f4773fa7f2e022ae164672b833c13f1f103f30cb --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2f649f59d1248b491c4ac73c4a6a221af6a878baac99a8305713bd5923646a7 +size 7788360 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0cb47f8271e399d38764948ce1b1265fa42f0408 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397632, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_12.json": { + "num_bytes": 8394845, + "checksum": null + } + }, + "download_size": 8394845, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15792477, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397632, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a176f78f87df70262278afc99835f3d9d2e35f74 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "3e8e033e065f0584", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..cb61010e03b01f63739237f0b7657007aa5eec9e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..00e4dc96a2df222b1d55b6c10993a7b33a116b2c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a0396d8658ed3a9cc7fe40c6e1e6aad017fff1df6e2d05861610d91c5cbcc1 +size 2000872 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3ba2743fc96272bc826d956c982ad631ca88ba3a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8fd1f1aa73b9b360835a250a517ad55d17c4685411e48da2b00b657bc09f139 +size 1894008 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..cb56e3430fe01af636870748b1d24fcf35f934ee --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:277f18494783cdde828eea3a28b451af3a446674140818e200d88805ce03b5fb +size 1934344 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..45f38194521b9441f675ff156f9ab8c0301bb530 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/cache-f777e0a36e1ce74a_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7b8c29e547f0692dfc1d6df354e5870bd05f3e745778e6bf392e639c7d0949 +size 1971600 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d0649f2644ef1ddb74d2881d692117c92c010852 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e85391f6cc866564793adffa586b7c47ba22198712bbf29d750836a54d6432 +size 7796856 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f78b91818c9ddac7f26fb418556b151338fe132 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7405908, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_13.json": { + "num_bytes": 8404811, + "checksum": null + } + }, + "download_size": 8404811, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15810719, + "splits": { + "train": { + "name": "train", + "num_bytes": 7405908, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..99fb80242f4973dd2219d5ab20b61024a9aed574 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "a68f893a934c5532", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ad381e32fe8ae4995be01322a0aa3edb2c2fb3ec --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..976c2e5835eff371f4880a21da52d5d37db14319 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a126bd74d3273d34ea54a6199d160867b4316809a2cce762fb487e44cb125b +size 1960296 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9ea378639ad5c7c00c863d5089a3e2ace90ce92e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdabb1cddc3817ca41745dd34ce97bac5b0e97c7f343faaac51c0ae66ab069d0 +size 2001072 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f40495297f6d8b0d180a042158003c6a6b99b9cf --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ca9caa5964988cd9da5a923db0f1ba7d8d34ccc04398af8a7d1959104843cd +size 1959448 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..df136f69441990eed7d566e25a7439ccad7f9ef2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/cache-a087e066492c66e0_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a18d0ab6408247f0498e7f29e0e168ab4485c959ec8a5fb3104def956d6337 +size 1999472 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5269d27432685c6057aebe169862690e6b206468 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b053af3851cc10ad9c572659099230432496e8a799d6f67401c75f9fd45cd97 +size 7916400 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1f5f31f242c6c70523b2b48d035593617db53e0d --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7526045, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_14.json": { + "num_bytes": 8519986, + "checksum": null + } + }, + "download_size": 8519986, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16046031, + "splits": { + "train": { + "name": "train", + "num_bytes": 7526045, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..3f12f6ebc3634396b61497d2ed5fe3acf534e4e4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "064ad2f648d02e6f", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..4360e7a1886abfd650e78de7c60c53d80f56b59c --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..aba897977974a01bee80b943fb8c8c1540d3ed04 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657e1d53f141579041e5ccbb0e0a42064abf2b291a1e30141e001e8c297bfb11 +size 2026816 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b1994f2f990fa811eadc0fd2312f7507baeebc0e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:186518f720eb96467858cc9001660aecf8a813ade16189bb29bbf96ef6a7084c +size 1925440 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1b8b80b66b7f0bacd1856709b523f1c1afae5da8 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a3a8213154203d7635b385020e5649173c13a9a26e0a344f6ce6ac53161524c +size 1906400 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0566735f47e6ebb14df928720b6ead41aa4b29d6 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/cache-5a17233a997b722d_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c298d13ae81f2134a8f34c9b73e1341a303c1b088626f415148649306477a0e +size 1990056 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..221b890796d6e3ad746bf10383052f1e3d13673d --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052d36824a197d1aa57c0dd4bb9871f4ef872008ab3ae348952e45cd36082f59 +size 7844816 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..675c725ffcab63a63c7f6040add40f629c6302f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7455328, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_15.json": { + "num_bytes": 8440301, + "checksum": null + } + }, + "download_size": 8440301, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15895629, + "splits": { + "train": { + "name": "train", + "num_bytes": 7455328, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a73e739f8a71cf4248566bc975f4a02bac3d2872 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "e7f0026d9f62bf32", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..7a88ddc5d9f5c280326345cffe59ccf0271d4eb0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b2eacfb6c50608b3737ceafb28602aab20065da1 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ea9446a08283e38b39cb042b29f0cc61c926ec5a756310d20441e8e4517cb3 +size 2003056 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..636ff4d9e2d65730b347649e430bc084ccf41d7f --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ed2fe607ca2cf2d636b55e701cc4fdb94618e9662e772928fb336f7b149f6b7 +size 1902352 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..897dd1a60d0dcc85e1556c569a517b3edb2977c2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31ba291ef8d5f50c9c54850fd818275109b3f713a64fad7e7d24ab53dffe53f +size 2007232 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9033f84efbe2e19234201c64ac74d4faabcd9258 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/cache-b95783e9d3ebbb6b_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05a0e3037e406a62369fb9877f76e1515e93c3e21c4d66937f7d248396f06d24 +size 1994296 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..eaae12b9710dd0611f844641402dbe8574803028 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d21283b1632305c4aecf16e7d57f32a93be553cc2a632dcb67d4a3502baa7e5 +size 7902976 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b0f5212e00804091a41e20f5b4a1681e679ecc --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7514211, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_16.json": { + "num_bytes": 8497254, + "checksum": null + } + }, + "download_size": 8497254, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16011465, + "splits": { + "train": { + "name": "train", + "num_bytes": 7514211, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..208a4cebdd3a1f16b6a5796f3931c167f72652e4 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "c8618e708a1125d8", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..503b84eae2968e4af2eaeae65ff4997c45ccccd2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b267293e91043cfe3887fe91d1db1835f2cff439 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:886666bdf17dd2ea161fd0edea26da2da65aef96724940b782fb765fe2bb9a23 +size 2027024 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f67caa3cece191f3e8eb1202af83c314b6027d2a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210fab39fefa1762ec22f1301e2d6a5350fec570095c68c5804b2070d3ab132e +size 1878128 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..d0927e2442efd7bccbf103aa8f79257482b841e2 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9ff8562e1c8aef5dd838a06f80c4d5d3ade7e5bf208bd08f85f2d0482b1445 +size 1877016 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..27604a1eb8efb3989f776f39dcff9b803f75644e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/cache-9ea26addf79f8120_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:864acbcb7a8c37a0fe4ba1b0153c1564669df27c6d4afebf0f64b7cae411d126 +size 1955048 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bf3bc58a1228e8773b04a5a2937c4a9a936f885a --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edd3dafadb6841ce6832b69a4b26f7a5c12fc6cc186dacbf2777df9e35236bf +size 7733216 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a8862d6bc73fa2e77d2f630e5d6a883d312222 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7342615, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_17.json": { + "num_bytes": 8337621, + "checksum": null + } + }, + "download_size": 8337621, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15680236, + "splits": { + "train": { + "name": "train", + "num_bytes": 7342615, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..7a3d89eb0085bf4171eb49a2519732b59a217b4f --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "f1f82ccaa2d669b7", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..e298e3110c13dbf2be88fde8b511a216bff3c9aa --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a77ad6f21559ff2077866b5a5b4adc82784c2aa0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd809aad1cb3deab0e51f32691e16f8cc8249f15c8cb4eaa9713df88b926eff5 +size 2019904 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..6a3637339120b034deb7b0ddda80b36cd881c9f3 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7c192b065a46cce02fb20030a7d95a425f6b45770c4b3fa2738e6031e91bf19 +size 2012016 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f20acef855a3ee6d0540501b516841173597ec0b --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9cb26a08153efedead6ca97fdec1d8ae72c30d76f24459f2a4673f028d76e0 +size 1932408 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b48842c2a9f11d2a7aaa7927a15b79b55ea6c2b0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/cache-976b9e88cdd45fec_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc30fc476b206c608c759cfae89624b764a3cd38050a7e86a64180356f77008c +size 1988888 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..519387caa45b964bae748dafc751a37afd0ce118 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1927175d74f787a913d47cde8eec4dcfe36d610b6ce102f9fcf1b5f707dd1da7 +size 7949272 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb216f3b809932dbb778e54c17010ffdd06444e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7559827, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_18.json": { + "num_bytes": 8548766, + "checksum": null + } + }, + "download_size": 8548766, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16108593, + "splits": { + "train": { + "name": "train", + "num_bytes": 7559827, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..240753d06bff2c895aeafe608af0489917c5a5cb --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "3ec0fee7f2f41507", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..06f89cfbb73e6305a22c86cc83b3d15373e7f7aa --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00000_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00000_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1f7f564606000365d1c2bf70bf69ee5f1d66a4b3 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00000_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d84cf1f8712795a4a2e124c913f55eef39637c5e6f1150aa995a3f6746abbd6 +size 1909088 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00001_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00001_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..602c5e04b226679c74271a986c3e87a3ab837e2e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00001_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379f5e28f91fda830c7f221fd78692608c0a1e19be215b85698812caa2bfc5bd +size 1892576 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00002_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00002_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ccbf88abc9855cddf439f9080043841d397d769f --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00002_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bef2ed68e89b8d37e444cc84141b3c7de7b378332f85a0b06d1a88de3eae39c +size 2012760 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00003_of_00004.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00003_of_00004.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e0730ceccf71427fb136247f19f62c7bf90651e0 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/cache-831cea3f768a156b_00003_of_00004.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36aada2ffa02f8d012d45cfcc587d488bb781cd50ab586a6927977830c6b7c53 +size 2019728 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..14d999cf9a70c831348a30065052c88681b7ed3e --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca8aa64895255bc91d19ab63ea74bf9dc2061da454db7f842ee5c3bbb32acfc +size 7830288 diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/dataset_info.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..51324591261cbedeaab4bf3cae73c0469c97e026 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7441014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_19.json": { + "num_bytes": 8427096, + "checksum": null + } + }, + "download_size": 8427096, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15868110, + "splits": { + "train": { + "name": "train", + "num_bytes": 7441014, + "num_examples": 5676, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/state.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..f4f5a4b97648fcb28cbc6e1c72c184bb6288f121 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "4cfbea3b61a99c53", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..0ed8d06baf31cbd724c8dfc09aa25f107f51f801 --- /dev/null +++ b/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json @@ -0,0 +1,13 @@ +{ + "v3_patch_version": 1, + "mode": "video", + "sem_per_tile": 81, + "sem_per_frame": 81, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train", + "rows": 5676, + "limit": null, + "timestamp": "2026-04-23T01:14:16", + "backfilled": true +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_2/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9a9811fb3b0f9ef498b2732d85c87fb7ed9d8ca5 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a08e569ce08479fba4ad3565bdf3592cd4cfc1d04d8a4c6bfcc047242272a1b +size 69352320 diff --git a/vmllm_cached/siglip2_v3_4_2/image_10pct/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_2/image_10pct/train/state.json b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..582e80470c4f235e38a3af933d3e6be72ed0f738 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "293d2d32c7066ab2", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_2/image_10pct/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..db6a2b9ae08f942111a72c07a1334b35abbac5b9 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_2/image_10pct/train/v3_patch_meta.json @@ -0,0 +1,14 @@ +{ + "v3_patch_version": "v3_4_2", + "mode": "image", + "geo_per_tile": 729, + "sem_per_tile": 81, + "per_tile_v3_4_2": 810, + "tile_size": 384, + "vision_aspect_ratio": "anyres_max_9", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/image_10pct/train", + "rows": 73859, + "limit": null, + "timestamp": "2026-04-27T11:46:58", + "formula": "lengths[0] += n_tiles * (GEO_PER_TILE + SEM_PER_TILE) - stock_packed_image" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..90f13ace671251dc32393ee012d807963ed6df0f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe351547c54e6ee0128daacbd4f05031d7b93cd2209bacaccf125ab296fa1ba +size 69352320 diff --git a/vmllm_cached/siglip2_v3_4_3/image_10pct/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/image_10pct/train/state.json b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..149eefaffcc7c81c47adedf087abc25301ec2da9 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "e970bd020257a531", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/image_10pct/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ffb69bd20bbf41d7864c2b51cb383fa1df1dc2c3 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/image_10pct/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "image", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/image_10pct/train", + "rows": 73859, + "lengths_sample_mean_old": 3667.28, + "lengths_sample_mean_new": 3668.28, + "timestamp": "2026-05-01T23:21:59" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a9b5cbda35a6d12b1b87fff3bd9c61eecc317d66 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10bba743278472a2cab959829f99842e37af7a3069bfc8d31869e114a16a7411 +size 7837872 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b59fb25a630e78cdaca99936940baa155b04ec05 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7447721, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_00.json": { + "num_bytes": 8441128, + "checksum": null + } + }, + "download_size": 8441128, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15888849, + "splits": { + "train": { + "name": "train", + "num_bytes": 7447721, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..08cea3c670c45a220d86b4c0a1934531202ed573 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "d3582d82e7e0f4b8", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..1829fb7aa057362e86ff6149cf7ba6fcc6e9483f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_00/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train", + "rows": 5681, + "lengths_sample_mean_old": 4710.91, + "lengths_sample_mean_new": 4726.91, + "timestamp": "2026-05-01T23:22:08" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8a067f11897ddd999d95363118ffc3d42327516d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a667f19acc24ff98a6142afae842d160e6ce25b85dc841c61d5ded952c924604 +size 7760272 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..9753431187f753de6088f363a3c32dc44a55eac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7368826, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_01.json": { + "num_bytes": 8374839, + "checksum": null + } + }, + "download_size": 8374839, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15743665, + "splits": { + "train": { + "name": "train", + "num_bytes": 7368826, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..974468dcadc69d7535f8aea934b7e9276450a7fd --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "5e0c5aca167e4853", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..9d904fc507598d8bd21278bcf26e9527219bf017 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_01/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train", + "rows": 5681, + "lengths_sample_mean_old": 4719.39, + "lengths_sample_mean_new": 4735.39, + "timestamp": "2026-05-01T23:22:09" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..065d071340c18b7f41276574bf2218541543f564 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44aae44307fb81cab78bc96f46238d74efd814fd9273c9a4fe29fa73e863c4c8 +size 7853432 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6f954de72e7e74d0f41e01d288d7974880fca499 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7463924, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_02.json": { + "num_bytes": 8451092, + "checksum": null + } + }, + "download_size": 8451092, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15915016, + "splits": { + "train": { + "name": "train", + "num_bytes": 7463924, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..d6d21e10ac2fb338ef86d1d4407e4353d82e670b --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "41ff844a233bfd5c", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..7352d292a93122d92cd2cd635b87723ce9ae38f9 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_02/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train", + "rows": 5681, + "lengths_sample_mean_old": 4675.45, + "lengths_sample_mean_new": 4691.45, + "timestamp": "2026-05-01T23:22:09" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..80a62c602e847860de34db2568c680e7cfc26548 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8de50d6f2f1030b61ff5ace317985cf635349e1ef4622f30b7cdbb4f2ea784 +size 7934096 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7857d783c3661746d540b0aefc631a9bf2e0598b --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7544302, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_03.json": { + "num_bytes": 8531728, + "checksum": null + } + }, + "download_size": 8531728, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16076030, + "splits": { + "train": { + "name": "train", + "num_bytes": 7544302, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..1abebdb10509e4ff00f76d0b7c151d44d1a68e05 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "e357d5500adcc5fa", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..94ab9c2d4359d5f89a7c7c180a521d6bf39eccb3 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_03/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train", + "rows": 5681, + "lengths_sample_mean_old": 4678.52, + "lengths_sample_mean_new": 4694.52, + "timestamp": "2026-05-01T23:22:10" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3fca30e78d6580140d1d5ee951844ce21fe6a211 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0258e8c96a8d9c5e2ece15ed307e2050b30e8b5446f0f3acc99cb6815bac410e +size 7676528 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..da60ed10e3f50ccfa09894c94607d3c1f63dd2f0 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7285950, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_04.json": { + "num_bytes": 8279218, + "checksum": null + } + }, + "download_size": 8279218, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15565168, + "splits": { + "train": { + "name": "train", + "num_bytes": 7285950, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e2a5c1222ccfcd2e945f879ff5642610de19de3f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "eca8c73888621bb3", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..0188ae3b1dd6d612088422795db52159ad1d4bc8 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_04/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train", + "rows": 5681, + "lengths_sample_mean_old": 4726.91, + "lengths_sample_mean_new": 4742.91, + "timestamp": "2026-05-01T23:22:11" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..dd24e1e8b4dc7a2813a5cf8c1dc7e08552271b3c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07af33e47ade4f4a8b397f185585c73d1d7e521f4bbde71732a4f24cbedb6e4 +size 7741288 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4a6592669cf04d687175727a1242a3157f1f9fc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7351520, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_05.json": { + "num_bytes": 8342040, + "checksum": null + } + }, + "download_size": 8342040, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15693560, + "splits": { + "train": { + "name": "train", + "num_bytes": 7351520, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..6454084905d0173d64217e140629457a112540d9 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "feaec53fe4ba02d1", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..e5f5ddf7e2767ac5435b4d37f9238d40927b7d5e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_05/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train", + "rows": 5681, + "lengths_sample_mean_old": 4700.79, + "lengths_sample_mean_new": 4716.79, + "timestamp": "2026-05-01T23:22:11" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1b664b417920be4bfcde3791147280a37bed1ebb --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7a97afb0ba9ad36b4c7c46f92932fb1dd73eebf30ca294d39a211ddcbc17b0 +size 7977632 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e4d829e34a1aabe81e5ecc49b355c8a6a3840114 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7588693, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_06.json": { + "num_bytes": 8571022, + "checksum": null + } + }, + "download_size": 8571022, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16159715, + "splits": { + "train": { + "name": "train", + "num_bytes": 7588693, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5ac844a931df3a0921679d7d96e5931e7a7f96fb --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "318dc3b0f5310e74", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..9d78bf21f196ed032e2edb01773aa8548b1cec72 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_06/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train", + "rows": 5681, + "lengths_sample_mean_old": 4728.08, + "lengths_sample_mean_new": 4744.08, + "timestamp": "2026-05-01T23:22:12" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e9485e0907b2b8c9833f8ab42e1520881494a80e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d00aaccb56f27396b4e887ffd24c84bbde215082f21454af4e9f45c05badc2e +size 7979912 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..07000a9a735529ddee3ce91d219dae59261506ee --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7590275, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_07.json": { + "num_bytes": 8581233, + "checksum": null + } + }, + "download_size": 8581233, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16171508, + "splits": { + "train": { + "name": "train", + "num_bytes": 7590275, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..aead4275ae29d25ce310e63dc851e7b57dc73c65 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "7c2a23801b08b920", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..011b6a0dfd56a15d0ba57427c5e09f2fcb5bc035 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_07/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train", + "rows": 5681, + "lengths_sample_mean_old": 4763.97, + "lengths_sample_mean_new": 4779.97, + "timestamp": "2026-05-01T23:22:13" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..da5b076d93ebaf32a405766679101079a911af58 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6525c4d8613bb09bf371480e437c52f988365973f68fcb718ed7ae39b3b473e +size 7878016 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..85586e975ae9411d5ea80ea7035380bbc3b37566 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7487777, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_08.json": { + "num_bytes": 8478861, + "checksum": null + } + }, + "download_size": 8478861, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15966638, + "splits": { + "train": { + "name": "train", + "num_bytes": 7487777, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..59e626dff108810b292fc4f6d941b8462b7f6819 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "4d476a2f7278bfc4", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..b757f399401492701fa250a6213f3ba64ea385cc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_08/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train", + "rows": 5681, + "lengths_sample_mean_old": 4719.25, + "lengths_sample_mean_new": 4735.25, + "timestamp": "2026-05-01T23:22:13" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ea431d7a85581cbfe711a7080f0957ee96206eef --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f123606ffc774506d7f07685d5d4553c79f1d68f0870de1f6748bb4884fbb38 +size 7931944 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5e87277e15cf2bf55a0f54ba7bff9f233d97cd61 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7541773, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_09.json": { + "num_bytes": 8536644, + "checksum": null + } + }, + "download_size": 8536644, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16078417, + "splits": { + "train": { + "name": "train", + "num_bytes": 7541773, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e8f4f4287ffe0dd92e945ad64a81236e928c97fa --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "172983c9230f1f1f", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..4b8627389d731b64058717d59c4d67967ad19fbe --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_09/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train", + "rows": 5681, + "lengths_sample_mean_old": 4719.52, + "lengths_sample_mean_new": 4735.52, + "timestamp": "2026-05-01T23:22:14" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..41ef72c278a8ec952613820947256e800eec7ac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49efc676c86966612f4cd1993c1542993b9e51466fa51cd1f7046bb5b27033da +size 8073904 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..782f0e4335635fefec72255602260ddc4dce4908 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7684339, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_10.json": { + "num_bytes": 8671454, + "checksum": null + } + }, + "download_size": 8671454, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16355793, + "splits": { + "train": { + "name": "train", + "num_bytes": 7684339, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c0f66d56d6c1792b7b8129e5dfb393a70866cb05 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "c261cf646cf21e83", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..a184b332051b74ad039a991b4f534d77facccfc1 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_10/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train", + "rows": 5681, + "lengths_sample_mean_old": 4746.13, + "lengths_sample_mean_new": 4762.13, + "timestamp": "2026-05-01T23:22:15" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b0c2e8f230c7a791f0a4477488981215f99418f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ee2802e0d5a355bc830b46e26ae6d5f3c42facd764b2b6f5eb77a97d44dcb8 +size 7786696 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..565f5f20807c6a25464f4ec2d6c6ac2423d47d83 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_11.json": { + "num_bytes": 8385641, + "checksum": null + } + }, + "download_size": 8385641, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15782655, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397014, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b6b0a08bd743025b01d6dfecb6ae1d06fc84bd6f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "53a70841e555dbf2", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..4e9ffe69c54aa6c65a474e5fcad2e65c47c25dbe --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_11/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train", + "rows": 5681, + "lengths_sample_mean_old": 4706.52, + "lengths_sample_mean_new": 4722.52, + "timestamp": "2026-05-01T23:22:15" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..92dc59c4c528b5b60bd2814c1bf173796205c89d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d359a22ca67deaf4527ad05f0b8567ae1d3d4327ac643d4e7a89e914ae33bb1 +size 7788360 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0cb47f8271e399d38764948ce1b1265fa42f0408 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397632, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_12.json": { + "num_bytes": 8394845, + "checksum": null + } + }, + "download_size": 8394845, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15792477, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397632, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..8b18cb4aee2462ab93ce2e6a5c95b584535fc24e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "ca2339f0eaf603ed", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..b6fd9dc1ec92b50243ca8d191030288ef33748ba --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_12/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train", + "rows": 5681, + "lengths_sample_mean_old": 4655.01, + "lengths_sample_mean_new": 4671.01, + "timestamp": "2026-05-01T23:22:16" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..00d7e9fce87b88bf0c5118984409a7c425d808e6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896c89e88839a09fe55259814effa34c41299ca69ddbd6ffad7898a55da89cd0 +size 7796856 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f78b91818c9ddac7f26fb418556b151338fe132 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7405908, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_13.json": { + "num_bytes": 8404811, + "checksum": null + } + }, + "download_size": 8404811, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15810719, + "splits": { + "train": { + "name": "train", + "num_bytes": 7405908, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b21a99e080273b9280079cd5fa57ddb19beaa155 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "9517cf478eae0d30", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..518119dbe04818716a5a8b81f1433ad172f2bfea --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_13/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train", + "rows": 5681, + "lengths_sample_mean_old": 4725.66, + "lengths_sample_mean_new": 4741.66, + "timestamp": "2026-05-01T23:22:17" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e09ee95c49cbb5fc3b8893dc3f14adb8c9dbfb2c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21dbc101e769ae2e59afb8eaae5bdaf07b67cd7938f03e5cb1612458c6690f59 +size 7916400 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1f5f31f242c6c70523b2b48d035593617db53e0d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7526045, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_14.json": { + "num_bytes": 8519986, + "checksum": null + } + }, + "download_size": 8519986, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16046031, + "splits": { + "train": { + "name": "train", + "num_bytes": 7526045, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c9fd5aaef872c76c4c5584bc9bc2c975038051bd --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "b5f33cbc6a15bd7a", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..6726d91299df5413461199a261ebe8c05fe7c778 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_14/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train", + "rows": 5681, + "lengths_sample_mean_old": 4692.02, + "lengths_sample_mean_new": 4708.02, + "timestamp": "2026-05-01T23:22:17" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8c4214ca0b37301d49846ffdbcc2926340118dcb --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb47bd2781e003c0026bd11142fc3131f9c1eee82eba62900010f4ef8bccf46f +size 7844816 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..675c725ffcab63a63c7f6040add40f629c6302f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7455328, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_15.json": { + "num_bytes": 8440301, + "checksum": null + } + }, + "download_size": 8440301, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15895629, + "splits": { + "train": { + "name": "train", + "num_bytes": 7455328, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5aa67204a219b845e419723af4f3bbc9c4e3e311 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "4d3d92c964e571f4", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..bd3088cb21bc59a7d5079772a08db369aa0e359a --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_15/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train", + "rows": 5681, + "lengths_sample_mean_old": 4740.22, + "lengths_sample_mean_new": 4756.22, + "timestamp": "2026-05-01T23:22:18" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8db878524f28bcbfb52b3a123ad6956440d8b17f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2869c61f2b0c5bb53bc5ee270efc5e55f7e451c3aa46059c966df9c72b4d774 +size 7902976 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b0f5212e00804091a41e20f5b4a1681e679ecc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7514211, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_16.json": { + "num_bytes": 8497254, + "checksum": null + } + }, + "download_size": 8497254, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16011465, + "splits": { + "train": { + "name": "train", + "num_bytes": 7514211, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..36aa6c2baf0d22f173df9c1483c8e856e8a9b49a --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "552e0be645023815", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..dd3f6ebd4bd0c21ac177a743a200f3222fbf582a --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_16/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train", + "rows": 5681, + "lengths_sample_mean_old": 4713.89, + "lengths_sample_mean_new": 4729.89, + "timestamp": "2026-05-01T23:22:19" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f55ba50f3b28c766a88f0478d20eba84835a2b7d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8e24d79448997f2c403478922228df1122472a8fa2b3288921df4260c0d554 +size 7733216 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a8862d6bc73fa2e77d2f630e5d6a883d312222 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7342615, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_17.json": { + "num_bytes": 8337621, + "checksum": null + } + }, + "download_size": 8337621, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15680236, + "splits": { + "train": { + "name": "train", + "num_bytes": 7342615, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..21be84085af5bdb04280e47e6272ce488910af12 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "558084371a74f0e1", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..aebfa8c3d9b29037a016bb940e99a877efece9de --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_17/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train", + "rows": 5681, + "lengths_sample_mean_old": 4704.96, + "lengths_sample_mean_new": 4720.96, + "timestamp": "2026-05-01T23:22:19" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..92dc9c342650597cfc61449ce2fe50d4a8d064c0 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e429c7ddf38be721d60124650a15d3fba8458a4e2196c458e4e229311d005fc8 +size 7949272 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb216f3b809932dbb778e54c17010ffdd06444e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7559827, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_18.json": { + "num_bytes": 8548766, + "checksum": null + } + }, + "download_size": 8548766, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16108593, + "splits": { + "train": { + "name": "train", + "num_bytes": 7559827, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..e5e514cf08a958d99cbedc47adb5f9873d1089b9 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "86c053585939a423", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..fa06f6ddd13bb2eb82ae85bfa809ac58e63a6c4b --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_18/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train", + "rows": 5681, + "lengths_sample_mean_old": 4666.67, + "lengths_sample_mean_new": 4682.67, + "timestamp": "2026-05-01T23:22:20" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..14cc7d62fc0df57d52da62073c4e604a1ed63bed --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584115befc9ab5b930026422a9d6c82f9f70342542a09f6a6d65d773e52dc15f +size 7830288 diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..51324591261cbedeaab4bf3cae73c0469c97e026 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7441014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_19.json": { + "num_bytes": 8427096, + "checksum": null + } + }, + "download_size": 8427096, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15868110, + "splits": { + "train": { + "name": "train", + "num_bytes": 7441014, + "num_examples": 5676, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/state.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..173b9e7f0253fb40f22e4a282038caa36217ce62 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "7aab3f7d04eaefd1", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..fdc9fa51104c2959bdd38aeedfceeb239259ee44 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_3/video_10pct_chunks/chunk_19/train/v3_patch_meta.json @@ -0,0 +1,11 @@ +{ + "v3_patch_version": "v3_4_3_fast", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "delta_formula": "image: lengths[0] += 1 * len(images); video: lengths[0] += 16 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train", + "rows": 5676, + "lengths_sample_mean_old": 4692.02, + "lengths_sample_mean_new": 4708.02, + "timestamp": "2026-05-01T23:22:21" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..5f7da7dbfb24058d27afd04cfd67423e02aa239c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f425fe7d09ad7d63e90ef2521e370dc0e3cf8acb71d4e5979a57ad198f684f8 +size 69352320 diff --git a/vmllm_cached/siglip2_v3_4_4/image_10pct/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/image_10pct/train/state.json b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..9c25a1286b99b35dceddcb8acd8494acdba6da86 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "6ff0cb43d943bef1", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/image_10pct/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..60af1dd208ffafc411e80b1f87984996344b6c17 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/image_10pct/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "image", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": null, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/image_10pct/train", + "rows": 73859, + "limit": null, + "timestamp": "2026-05-04T17:12:23", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a9b5cbda35a6d12b1b87fff3bd9c61eecc317d66 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10bba743278472a2cab959829f99842e37af7a3069bfc8d31869e114a16a7411 +size 7837872 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b59fb25a630e78cdaca99936940baa155b04ec05 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7447721, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_00.json": { + "num_bytes": 8441128, + "checksum": null + } + }, + "download_size": 8441128, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15888849, + "splits": { + "train": { + "name": "train", + "num_bytes": 7447721, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0c0d8d9292346f1491db088f140cd6ce83daf863 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "b08da3e4958b57bb", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..715ad3d2d31d07dd48eacece748de5dbfc53e104 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_00/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_00/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:28", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8a067f11897ddd999d95363118ffc3d42327516d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a667f19acc24ff98a6142afae842d160e6ce25b85dc841c61d5ded952c924604 +size 7760272 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..9753431187f753de6088f363a3c32dc44a55eac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7368826, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_01.json": { + "num_bytes": 8374839, + "checksum": null + } + }, + "download_size": 8374839, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15743665, + "splits": { + "train": { + "name": "train", + "num_bytes": 7368826, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..7246deadc69ed998dcdee057a9b3664aebb36359 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "87b300b8672a317f", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..181dacf2504c3790e1b32fe305f5eb3309c2494e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_01/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_01/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:33", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..065d071340c18b7f41276574bf2218541543f564 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44aae44307fb81cab78bc96f46238d74efd814fd9273c9a4fe29fa73e863c4c8 +size 7853432 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6f954de72e7e74d0f41e01d288d7974880fca499 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7463924, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_02.json": { + "num_bytes": 8451092, + "checksum": null + } + }, + "download_size": 8451092, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15915016, + "splits": { + "train": { + "name": "train", + "num_bytes": 7463924, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..77875f7a7b83e38d94c152f4ab9a12b3b7aa7745 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "660215006af14abb", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..355e5dae7657fe7ce31fb49f9331b523d5869573 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_02/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_02/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:38", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..80a62c602e847860de34db2568c680e7cfc26548 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c8de50d6f2f1030b61ff5ace317985cf635349e1ef4622f30b7cdbb4f2ea784 +size 7934096 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7857d783c3661746d540b0aefc631a9bf2e0598b --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7544302, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_03.json": { + "num_bytes": 8531728, + "checksum": null + } + }, + "download_size": 8531728, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16076030, + "splits": { + "train": { + "name": "train", + "num_bytes": 7544302, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..fa5524788558098c3713c1c452de50f2f7775e6e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "7b06f8393f6ce5f5", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..9ce530ec63bb87521f6c442aef60f52012bc2890 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_03/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_03/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:43", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..3fca30e78d6580140d1d5ee951844ce21fe6a211 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0258e8c96a8d9c5e2ece15ed307e2050b30e8b5446f0f3acc99cb6815bac410e +size 7676528 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..da60ed10e3f50ccfa09894c94607d3c1f63dd2f0 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7285950, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_04.json": { + "num_bytes": 8279218, + "checksum": null + } + }, + "download_size": 8279218, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15565168, + "splits": { + "train": { + "name": "train", + "num_bytes": 7285950, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..fbbff877d732f98cedab9d4fea10e739e3947c6c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "4275f7db5d41c171", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..f1e32c38e0a001608f111a4ba1181043e1571606 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_04/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_04/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:48", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..dd24e1e8b4dc7a2813a5cf8c1dc7e08552271b3c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c07af33e47ade4f4a8b397f185585c73d1d7e521f4bbde71732a4f24cbedb6e4 +size 7741288 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4a6592669cf04d687175727a1242a3157f1f9fc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7351520, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_05.json": { + "num_bytes": 8342040, + "checksum": null + } + }, + "download_size": 8342040, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15693560, + "splits": { + "train": { + "name": "train", + "num_bytes": 7351520, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..6cd812deb115433cbfd2d3df25a020c8d22198dc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "f74ae81c7c54a12d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..629f1bd91b027b2fce0174a5db68e25202fab06c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_05/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_05/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:53", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..1b664b417920be4bfcde3791147280a37bed1ebb --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7a97afb0ba9ad36b4c7c46f92932fb1dd73eebf30ca294d39a211ddcbc17b0 +size 7977632 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e4d829e34a1aabe81e5ecc49b355c8a6a3840114 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7588693, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_06.json": { + "num_bytes": 8571022, + "checksum": null + } + }, + "download_size": 8571022, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16159715, + "splits": { + "train": { + "name": "train", + "num_bytes": 7588693, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..95a1260b19053b54359770ce8f9c6d97db6a4bce --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "adcbbdd4a2f61d28", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..a94cce6580908ab64bdcc8898edd4d73bfbfe517 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_06/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_06/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:12:58", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e9485e0907b2b8c9833f8ab42e1520881494a80e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d00aaccb56f27396b4e887ffd24c84bbde215082f21454af4e9f45c05badc2e +size 7979912 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..07000a9a735529ddee3ce91d219dae59261506ee --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7590275, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_07.json": { + "num_bytes": 8581233, + "checksum": null + } + }, + "download_size": 8581233, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16171508, + "splits": { + "train": { + "name": "train", + "num_bytes": 7590275, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..af6d61b8837692e40c59d502b7bfe1ee57a597d2 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "06dfe0d5bf1f7ef3", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..e0b8093ca431bbc4caab0376b91f0fdad8bca961 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_07/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_07/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:03", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..da5b076d93ebaf32a405766679101079a911af58 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6525c4d8613bb09bf371480e437c52f988365973f68fcb718ed7ae39b3b473e +size 7878016 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..85586e975ae9411d5ea80ea7035380bbc3b37566 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7487777, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_08.json": { + "num_bytes": 8478861, + "checksum": null + } + }, + "download_size": 8478861, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15966638, + "splits": { + "train": { + "name": "train", + "num_bytes": 7487777, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..4d1cc39c2d6f43b5a7ffe42fb1bab5b68d79a96f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "45033e091ccb2a1e", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..74be919548291b6d4e6d3412a574e18ff344acb3 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_08/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_08/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:07", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ea431d7a85581cbfe711a7080f0957ee96206eef --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f123606ffc774506d7f07685d5d4553c79f1d68f0870de1f6748bb4884fbb38 +size 7931944 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5e87277e15cf2bf55a0f54ba7bff9f233d97cd61 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7541773, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_09.json": { + "num_bytes": 8536644, + "checksum": null + } + }, + "download_size": 8536644, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16078417, + "splits": { + "train": { + "name": "train", + "num_bytes": 7541773, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..de96d031a73a3cf31c05e9cc8577e9724cb016a5 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "9c01ae07970c312a", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..6e260b41789031b389cbcbe4b9399ffadb8fce9c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_09/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_09/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:12", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..41ef72c278a8ec952613820947256e800eec7ac6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49efc676c86966612f4cd1993c1542993b9e51466fa51cd1f7046bb5b27033da +size 8073904 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..782f0e4335635fefec72255602260ddc4dce4908 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7684339, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_10.json": { + "num_bytes": 8671454, + "checksum": null + } + }, + "download_size": 8671454, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16355793, + "splits": { + "train": { + "name": "train", + "num_bytes": 7684339, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0d96cdfcb8fa2af0e3877e811987dbb3dc9df229 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "2a6f3d7083990efc", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..036cafd739c07128f2f5aa19b88f3fd31ed998bf --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_10/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_10/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:17", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..b0c2e8f230c7a791f0a4477488981215f99418f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16ee2802e0d5a355bc830b46e26ae6d5f3c42facd764b2b6f5eb77a97d44dcb8 +size 7786696 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..565f5f20807c6a25464f4ec2d6c6ac2423d47d83 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_11.json": { + "num_bytes": 8385641, + "checksum": null + } + }, + "download_size": 8385641, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15782655, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397014, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..2279c96dd2105298084fb5883f16ffc09be621f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "dc954caf860a1c23", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..8827a2a2ee68c27d7894c10e21e4b5199dde9515 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_11/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_11/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:22", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..92dc59c4c528b5b60bd2814c1bf173796205c89d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d359a22ca67deaf4527ad05f0b8567ae1d3d4327ac643d4e7a89e914ae33bb1 +size 7788360 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0cb47f8271e399d38764948ce1b1265fa42f0408 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397632, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_12.json": { + "num_bytes": 8394845, + "checksum": null + } + }, + "download_size": 8394845, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15792477, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397632, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..0452ad3a816db169625162058905cbd6a135c51a --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "d89c123a1286c7d3", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..8ca9e494fbdd11f9edebc2afed5353641b344403 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_12/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_12/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:27", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..00d7e9fce87b88bf0c5118984409a7c425d808e6 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896c89e88839a09fe55259814effa34c41299ca69ddbd6ffad7898a55da89cd0 +size 7796856 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f78b91818c9ddac7f26fb418556b151338fe132 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7405908, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_13.json": { + "num_bytes": 8404811, + "checksum": null + } + }, + "download_size": 8404811, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15810719, + "splits": { + "train": { + "name": "train", + "num_bytes": 7405908, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..60a609d8322ba7be7d193ac194e4cd87e322a32f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "f777e0a36e1ce74a", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..e5ceb82c6b353fcb7b49dfe747be6a30bfc272f5 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_13/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_13/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:31", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..e09ee95c49cbb5fc3b8893dc3f14adb8c9dbfb2c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21dbc101e769ae2e59afb8eaae5bdaf07b67cd7938f03e5cb1612458c6690f59 +size 7916400 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1f5f31f242c6c70523b2b48d035593617db53e0d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7526045, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_14.json": { + "num_bytes": 8519986, + "checksum": null + } + }, + "download_size": 8519986, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16046031, + "splits": { + "train": { + "name": "train", + "num_bytes": 7526045, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b5a542a29d3e1751b416d03fc245bb8be428dc5e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "a087e066492c66e0", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..96aae659d1ec6ab03c573d18023daf01f03b0188 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_14/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_14/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:36", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8c4214ca0b37301d49846ffdbcc2926340118dcb --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb47bd2781e003c0026bd11142fc3131f9c1eee82eba62900010f4ef8bccf46f +size 7844816 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..675c725ffcab63a63c7f6040add40f629c6302f4 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7455328, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_15.json": { + "num_bytes": 8440301, + "checksum": null + } + }, + "download_size": 8440301, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15895629, + "splits": { + "train": { + "name": "train", + "num_bytes": 7455328, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..4947a53027406c07592b388c3ec7456e840fc218 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "5a17233a997b722d", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..5d428d8142bc2ce7d6d59d0bbb7963f15b1e0a2e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_15/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_15/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:41", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8db878524f28bcbfb52b3a123ad6956440d8b17f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2869c61f2b0c5bb53bc5ee270efc5e55f7e451c3aa46059c966df9c72b4d774 +size 7902976 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b0f5212e00804091a41e20f5b4a1681e679ecc --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7514211, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_16.json": { + "num_bytes": 8497254, + "checksum": null + } + }, + "download_size": 8497254, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16011465, + "splits": { + "train": { + "name": "train", + "num_bytes": 7514211, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5e4233eaa5bb259763999740a29401cfd1803769 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "b95783e9d3ebbb6b", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..3ea6fbcca2dea4604a1c177aaf3489e44b762f8c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_16/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_16/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:46", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..f55ba50f3b28c766a88f0478d20eba84835a2b7d --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8e24d79448997f2c403478922228df1122472a8fa2b3288921df4260c0d554 +size 7733216 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a8862d6bc73fa2e77d2f630e5d6a883d312222 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7342615, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_17.json": { + "num_bytes": 8337621, + "checksum": null + } + }, + "download_size": 8337621, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15680236, + "splits": { + "train": { + "name": "train", + "num_bytes": 7342615, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a92d1fbab4f6b9407cdb66c9bdd9bfcf44c8a977 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "9ea26addf79f8120", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..f037ac5966b4112797e22c89762f4d1e83f684c5 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_17/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_17/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:51", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..92dc9c342650597cfc61449ce2fe50d4a8d064c0 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e429c7ddf38be721d60124650a15d3fba8458a4e2196c458e4e229311d005fc8 +size 7949272 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb216f3b809932dbb778e54c17010ffdd06444e --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7559827, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_18.json": { + "num_bytes": 8548766, + "checksum": null + } + }, + "download_size": 8548766, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16108593, + "splits": { + "train": { + "name": "train", + "num_bytes": 7559827, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a626b249a15bfc5087cd30fdbc0edaca18ca800a --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "976b9e88cdd45fec", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..d8d76f380842a56571d6eb26b94ca9c3bc28ee1f --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_18/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_18/train", + "rows": 5681, + "limit": null, + "timestamp": "2026-05-04T17:13:56", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..14cc7d62fc0df57d52da62073c4e604a1ed63bed --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584115befc9ab5b930026422a9d6c82f9f70342542a09f6a6d65d773e52dc15f +size 7830288 diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/dataset_info.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..51324591261cbedeaab4bf3cae73c0469c97e026 --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7441014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_19.json": { + "num_bytes": 8427096, + "checksum": null + } + }, + "download_size": 8427096, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15868110, + "splits": { + "train": { + "name": "train", + "num_bytes": 7441014, + "num_examples": 5676, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/state.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..088b8440752b7c8acdd859a89f1ec22e5081ec0c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/state.json @@ -0,0 +1,13 @@ +{ + "_data_files": [ + { + "filename": "data-00000-of-00001.arrow" + } + ], + "_fingerprint": "831cea3f768a156b", + "_format_columns": null, + "_format_kwargs": {}, + "_format_type": null, + "_output_all_columns": false, + "_split": null +} \ No newline at end of file diff --git a/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/v3_patch_meta.json b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/v3_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ff440c8fb70ae23b3988ff8e556da8eaee2c2a4c --- /dev/null +++ b/vmllm_cached/siglip2_v3_4_4/video_10pct_chunks/chunk_19/train/v3_patch_meta.json @@ -0,0 +1,16 @@ +{ + "v3_patch_version": "v3_4_4", + "mode": "video", + "from": "siglip2_v3 (V3 base)", + "sem_per_tile": 81, + "sem_per_frame": 81, + "sem_marker_per_tile": 1, + "sem_marker_per_frame": 1, + "num_frames": 16, + "tile_size": 384, + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2_v3/video_10pct_chunks/chunk_19/train", + "rows": 5676, + "limit": null, + "timestamp": "2026-05-04T17:14:00", + "formula": "image: lengths[0] += sum(max(0, n_tiles_i - 1)) per row (per-tile sem_marker, variable per image); video: lengths[0] += num_frames * SEM_MARKER_PER_FRAME * n_videos" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/image_10pct/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/image_10pct/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..0dcb20d2498396aa3f06c72c22d37e267dda5f71 --- /dev/null +++ b/vmllm_cached/vjepa21/image_10pct/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde6c7cd2ce6c46b02dec2761a3aad5040dc692cce2c7f97f505767f4c53a880 +size 69352320 diff --git a/vmllm_cached/vjepa21/image_10pct/train/dataset_info.json b/vmllm_cached/vjepa21/image_10pct/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..247c1c30e524c304f720fba9d5501512146bb7f2 --- /dev/null +++ b/vmllm_cached/vjepa21/image_10pct/train/dataset_info.json @@ -0,0 +1,65 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 66130519, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/image_sft_small_10pct_sharegpt.json": { + "num_bytes": 85235535, + "checksum": null + } + }, + "download_size": 85235535, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "images": [ + { + "bytes": { + "dtype": "null", + "_type": "Value" + }, + "path": { + "dtype": "string", + "_type": "Value" + } + } + ], + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 151366054, + "splits": { + "train": { + "name": "train", + "num_bytes": 66130519, + "num_examples": 73859, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/image_10pct/train/state.json b/vmllm_cached/vjepa21/image_10pct/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..4144e254f3c61cb69f654028e47661e59b6e1ced --- /dev/null +++ b/vmllm_cached/vjepa21/image_10pct/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "8b508c67f2fe56fe", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/image_10pct/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/image_10pct/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..7cb0e4aec1d1271fb041cfcb68b9c304b864b8ae --- /dev/null +++ b/vmllm_cached/vjepa21/image_10pct/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "image", + "from": "siglip2 (SigLIP2 base, num_image_tokens=729, video pool 14\u00b2)", + "to": "vjepa21 (V-JEPA 2.1 ViT-L, num_image_tokens=576, video tubelet skip-pool)", + "delta_formula": "image: lengths[0] += sum(per-image stock _get_number_of_features delta) (num_image_tokens 729 \u2192 576, via LlavaOnevisionProcessor method rebind to stub; captures unpadded + newline + base \u4e09\u9879 \u03b4)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/image_10pct/train", + "rows": 73859, + "lengths_sample_mean_old": 3245.27, + "lengths_sample_mean_new": 2624.35, + "timestamp": "2026-05-11T16:18:06" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..becc091a5fc82031039734f03f3377672be4b0fa --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b795496c9c302e4d189d3d026bf1e414700039878502561378ddf58362a7ab83 +size 7837872 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..b59fb25a630e78cdaca99936940baa155b04ec05 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7447721, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_00.json": { + "num_bytes": 8441128, + "checksum": null + } + }, + "download_size": 8441128, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15888849, + "splits": { + "train": { + "name": "train", + "num_bytes": 7447721, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..7cfc4cf53abc2ceb0e262203f840eb5508fbc794 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "fcdb0d51c472f4c5", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..ca7595473cb83bbe64ed69936075c1e50fd30cf5 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_00/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_00/train", + "rows": 5681, + "lengths_sample_mean_old": 3414.91, + "lengths_sample_mean_new": 4886.91, + "timestamp": "2026-05-11T15:38:42" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..bc19c76b8079166a1939e91188fde2023c1dfcbf --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0631e215c50f00f42c5c05c315bca64a097eb1ba41b7eb9ec83ddd1ca1a9409 +size 7760272 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..9753431187f753de6088f363a3c32dc44a55eac6 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7368826, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_01.json": { + "num_bytes": 8374839, + "checksum": null + } + }, + "download_size": 8374839, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15743665, + "splits": { + "train": { + "name": "train", + "num_bytes": 7368826, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..a40927967141fc6180f6556fa4d9c3690745e0c6 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "1fa6968a695d7ed9", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..4a21a73a25cc41e2eeb4dbb3dd1cb2b71e2b4a1d --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_01/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_01/train", + "rows": 5681, + "lengths_sample_mean_old": 3423.39, + "lengths_sample_mean_new": 4895.39, + "timestamp": "2026-05-11T15:38:54" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..30b817d35905c65b51333119cc2387ddf0d3a9e8 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2543b8b3429a0b696c74b11b53393d337f8682179423d3b2013708d59a0ab0d +size 7853432 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..6f954de72e7e74d0f41e01d288d7974880fca499 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7463924, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_02.json": { + "num_bytes": 8451092, + "checksum": null + } + }, + "download_size": 8451092, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15915016, + "splits": { + "train": { + "name": "train", + "num_bytes": 7463924, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..b33febbb73c9baf1a06fa5abd4124a111eadf40f --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "67922778fe789d97", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..b65b23d323b80a73e4988ac997c7ea4ca6521d8e --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_02/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_02/train", + "rows": 5681, + "lengths_sample_mean_old": 3379.45, + "lengths_sample_mean_new": 4851.45, + "timestamp": "2026-05-11T15:38:55" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2324cfeedd5f019e1b3c1e47d31883f380670b2d --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492dfdbc3d3fa27eab18aac4ba67a2deb3bf1d3b911d27885de11b3bb6bccafa +size 7934096 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..7857d783c3661746d540b0aefc631a9bf2e0598b --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7544302, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_03.json": { + "num_bytes": 8531728, + "checksum": null + } + }, + "download_size": 8531728, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16076030, + "splits": { + "train": { + "name": "train", + "num_bytes": 7544302, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..bb5c66de272cfaf073f54d537a6086e316a27c49 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "034aaf22051fa0ae", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..6d85706329f20f210ebc4343a97e68ebb7f1e9b1 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_03/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_03/train", + "rows": 5681, + "lengths_sample_mean_old": 3382.52, + "lengths_sample_mean_new": 4854.52, + "timestamp": "2026-05-11T15:38:56" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..21bdbd000d33473a02ff7ad5a67cb6ea69c82cd6 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22a22113c5e2e046241aff63714ddcd44cb8c8140e553aa9df7fc3f66128210 +size 7676528 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..da60ed10e3f50ccfa09894c94607d3c1f63dd2f0 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7285950, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_04.json": { + "num_bytes": 8279218, + "checksum": null + } + }, + "download_size": 8279218, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15565168, + "splits": { + "train": { + "name": "train", + "num_bytes": 7285950, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..950aca7fea932c8ab6eedf3d6f0edbe47dd01291 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "5fa0e5d6216678a0", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..32682f8175642962174a055ce604847f24edb4b6 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_04/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_04/train", + "rows": 5681, + "lengths_sample_mean_old": 3430.91, + "lengths_sample_mean_new": 4902.91, + "timestamp": "2026-05-11T15:38:56" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7168b1d901d4d451e84ffff83bd02c237132a87e --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762b517a0a1e6a9b326029cfd36d2887cccf8d0fe5ccd8764e902a33bcc898d4 +size 7741288 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4a6592669cf04d687175727a1242a3157f1f9fc --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7351520, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_05.json": { + "num_bytes": 8342040, + "checksum": null + } + }, + "download_size": 8342040, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15693560, + "splits": { + "train": { + "name": "train", + "num_bytes": 7351520, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..c531636bf9a4412fc56ff9cac4656ec7bfe5a1e4 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "b220e4881c83491d", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..3e3b8aee12bcd46c69aa1cd88a0989fd3e368b7c --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_05/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_05/train", + "rows": 5681, + "lengths_sample_mean_old": 3404.79, + "lengths_sample_mean_new": 4876.79, + "timestamp": "2026-05-11T15:38:57" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..466d9607bbede51a86083b6f2a883eb9dee26283 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47774d9c292ae6dd9207825f1449ac86267dafbcac1ad6534c05321c67af6f59 +size 7977632 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e4d829e34a1aabe81e5ecc49b355c8a6a3840114 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7588693, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_06.json": { + "num_bytes": 8571022, + "checksum": null + } + }, + "download_size": 8571022, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16159715, + "splits": { + "train": { + "name": "train", + "num_bytes": 7588693, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..9827cad7d9a0348a39e676050684ee392396a078 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "699bcf19aee2da88", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..f74c359c0869de81444dc54930569bf8e0628663 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_06/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_06/train", + "rows": 5681, + "lengths_sample_mean_old": 3432.08, + "lengths_sample_mean_new": 4904.08, + "timestamp": "2026-05-11T15:38:58" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..046126a688a6bc517f927b9b05bed4dc81f54853 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4612f3e5fb5d040685446c5a7b01a3bc0793307086fc6b7aff195914e3ce16 +size 7979912 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..07000a9a735529ddee3ce91d219dae59261506ee --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7590275, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_07.json": { + "num_bytes": 8581233, + "checksum": null + } + }, + "download_size": 8581233, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16171508, + "splits": { + "train": { + "name": "train", + "num_bytes": 7590275, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..97e9fff85351c36bb6addb181c78b11f04519671 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "f15df0b8a41351d5", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..a2d407aa91e00434ad5c5c071676cf3093904a5f --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_07/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_07/train", + "rows": 5681, + "lengths_sample_mean_old": 3467.97, + "lengths_sample_mean_new": 4939.97, + "timestamp": "2026-05-11T15:38:58" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..c6d9df8456cb65d377accb82d0e03e80cc120ebd --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50747840a95d741f81227cca68f4e2e3ea23d2b3753f9d2a0b0da046a5f9de02 +size 7878016 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..85586e975ae9411d5ea80ea7035380bbc3b37566 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7487777, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_08.json": { + "num_bytes": 8478861, + "checksum": null + } + }, + "download_size": 8478861, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15966638, + "splits": { + "train": { + "name": "train", + "num_bytes": 7487777, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..756a505fd813b204ee074b52d422db2b6d82dfdb --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "efb20606a7897f10", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..3f6c91a42ea3ece67f89496e2a964486bb9a0d30 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_08/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_08/train", + "rows": 5681, + "lengths_sample_mean_old": 3423.25, + "lengths_sample_mean_new": 4895.25, + "timestamp": "2026-05-11T15:38:59" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..560701c12dfeb7671e58d112b232cef63e175e03 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087cd98bc9fe8f0a0ec829c69a6cb3858308f95539634c3962e87d837a468ef3 +size 7931944 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..5e87277e15cf2bf55a0f54ba7bff9f233d97cd61 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7541773, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_09.json": { + "num_bytes": 8536644, + "checksum": null + } + }, + "download_size": 8536644, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16078417, + "splits": { + "train": { + "name": "train", + "num_bytes": 7541773, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..485058e4fabfe8fd7345ed50bf3f25060de43217 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "80f39657123e1abf", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..849309adac86a6211e6c3f385819a7d1165c020f --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_09/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_09/train", + "rows": 5681, + "lengths_sample_mean_old": 3423.52, + "lengths_sample_mean_new": 4895.52, + "timestamp": "2026-05-11T15:39:00" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..08120efa372acfbaf6501f8a76654daf90b5b1a4 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84196cb29e4f2b038df58d8b36196f09e2479b30da98901093e277dfbc766906 +size 8073904 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..782f0e4335635fefec72255602260ddc4dce4908 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7684339, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_10.json": { + "num_bytes": 8671454, + "checksum": null + } + }, + "download_size": 8671454, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16355793, + "splits": { + "train": { + "name": "train", + "num_bytes": 7684339, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..6d689805f77eb9ab275366d1fbdddff505fd6885 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "40d0c61caab0704d", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..cdc722b32c85bee0fcf768e21046fd7d6a355925 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_10/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_10/train", + "rows": 5681, + "lengths_sample_mean_old": 3450.13, + "lengths_sample_mean_new": 4922.13, + "timestamp": "2026-05-11T15:39:00" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..a08a3d27ba5544ab9eb93495c11047e26af4d731 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c9d335089cc30d89c1fadc34fa7ef9ec4892d7995bde9cb3e0186b9449b14e +size 7786696 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..565f5f20807c6a25464f4ec2d6c6ac2423d47d83 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_11.json": { + "num_bytes": 8385641, + "checksum": null + } + }, + "download_size": 8385641, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15782655, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397014, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..4c49f0e92255a0a719ed258a3f8c6101d5f9a83d --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "f24435657501f2f2", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..970b7fb13806c594ab3364b95fc538544a8bd402 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_11/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_11/train", + "rows": 5681, + "lengths_sample_mean_old": 3410.52, + "lengths_sample_mean_new": 4882.52, + "timestamp": "2026-05-11T15:39:01" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..529d1f95ebff21021040673a2f99cb95655bd83c --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f4b94e087f25942e59e0fe5bb89a165dc4895d3f0ba80c8c8c4988828e35b7c +size 7788360 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..0cb47f8271e399d38764948ce1b1265fa42f0408 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7397632, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_12.json": { + "num_bytes": 8394845, + "checksum": null + } + }, + "download_size": 8394845, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15792477, + "splits": { + "train": { + "name": "train", + "num_bytes": 7397632, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..56b72aa4f3a3a69d652bd10725fed38cfee7de28 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "6365462d25ec8cc5", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..a458010fcdc5f91a26a149f352b8df59da7d0738 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_12/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_12/train", + "rows": 5681, + "lengths_sample_mean_old": 3359.01, + "lengths_sample_mean_new": 4831.01, + "timestamp": "2026-05-11T15:39:02" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..cfc624dd138ca5cb5b8e50a22d565efa257d4217 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970c2e6e5faf45897b621a8e944522e087c5c45adb3aa4f7f7758291981b38b0 +size 7796856 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..3f78b91818c9ddac7f26fb418556b151338fe132 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7405908, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_13.json": { + "num_bytes": 8404811, + "checksum": null + } + }, + "download_size": 8404811, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15810719, + "splits": { + "train": { + "name": "train", + "num_bytes": 7405908, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..509133c1c2cef596c10f2e21401dca589273d4c5 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "b04b7839b157007f", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..9f7128940abfb1a5c91e25a207be92f656e08c0e --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_13/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_13/train", + "rows": 5681, + "lengths_sample_mean_old": 3429.66, + "lengths_sample_mean_new": 4901.66, + "timestamp": "2026-05-11T15:39:03" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..9980727cc7335962320bae74c223f3fc3df0647c --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ed357d1c95691d43205cfe2d39ddb7211c787b4b9337b25f338a1327b195de +size 7916400 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..1f5f31f242c6c70523b2b48d035593617db53e0d --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7526045, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_14.json": { + "num_bytes": 8519986, + "checksum": null + } + }, + "download_size": 8519986, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16046031, + "splits": { + "train": { + "name": "train", + "num_bytes": 7526045, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..466a76ddf445b40ce2ab66cc232a842441fbabf8 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "d18724de3192c0f7", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..4857888ce4b46fead88ec08d7873674045c8f0d3 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_14/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_14/train", + "rows": 5681, + "lengths_sample_mean_old": 3396.02, + "lengths_sample_mean_new": 4868.02, + "timestamp": "2026-05-11T15:39:03" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..7c5dc1c394705413239e08ca1c4fe76773caa18c --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7294c8ea9e50259f283327b010214a5ec00ba41fbfb0e4a0edc3d17de5872b +size 7844816 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..675c725ffcab63a63c7f6040add40f629c6302f4 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7455328, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_15.json": { + "num_bytes": 8440301, + "checksum": null + } + }, + "download_size": 8440301, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15895629, + "splits": { + "train": { + "name": "train", + "num_bytes": 7455328, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..5f7656db6f9be4ca4f69bc3841a864cbb1a175d8 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "46105b9ef5806df6", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..63ee985b9f882ba2310c5bceb8b04e34dfbc6ef4 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_15/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_15/train", + "rows": 5681, + "lengths_sample_mean_old": 3444.22, + "lengths_sample_mean_new": 4916.22, + "timestamp": "2026-05-11T15:39:04" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..2e86602049750ed6390875d627a249badea5f1f1 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78dbcf45290f6db4c3afa52c6c3703a80ae15287e34d09e65028b81f3d0460b0 +size 7902976 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..f4b0f5212e00804091a41e20f5b4a1681e679ecc --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7514211, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_16.json": { + "num_bytes": 8497254, + "checksum": null + } + }, + "download_size": 8497254, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16011465, + "splits": { + "train": { + "name": "train", + "num_bytes": 7514211, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..2c519a0676ecb1cf00b3b75bdfc63a2c2d4fce04 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "4042a93cddbe74a8", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..b36c72c4b79fa50c9db286aafe693504516faaa8 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_16/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_16/train", + "rows": 5681, + "lengths_sample_mean_old": 3417.89, + "lengths_sample_mean_new": 4889.89, + "timestamp": "2026-05-11T15:39:05" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..eb5828de7b511c25dc8e7a6de5de8402dd6dc2ab --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f6d8f0857d5a6d8434bd216846285a217f20d85ab0b3f864fcf710ae16bc9b +size 7733216 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..e5a8862d6bc73fa2e77d2f630e5d6a883d312222 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7342615, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_17.json": { + "num_bytes": 8337621, + "checksum": null + } + }, + "download_size": 8337621, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15680236, + "splits": { + "train": { + "name": "train", + "num_bytes": 7342615, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..1094604c484e52a4d3d76f46444ac95652fff379 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "f96e38d76f48af8c", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..dc1718e020c984f261ebe3c33d621bfbf356b5fc --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_17/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_17/train", + "rows": 5681, + "lengths_sample_mean_old": 3408.96, + "lengths_sample_mean_new": 4880.96, + "timestamp": "2026-05-11T15:39:05" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..8d14d3f45c5b0f5e62d2d421ec89bc63eed4dd6d --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd67c96d5816dca61016612495ee8b6810b47ccd13afb295a07db89cdf1437c5 +size 7949272 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..ddb216f3b809932dbb778e54c17010ffdd06444e --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7559827, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_18.json": { + "num_bytes": 8548766, + "checksum": null + } + }, + "download_size": 8548766, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 16108593, + "splits": { + "train": { + "name": "train", + "num_bytes": 7559827, + "num_examples": 5681, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..351781f04e8232e3a960909a8262116b132889f8 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "34f2ad302a987515", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..04f64fe21ee40369e0eda8f7464719b582e8ae9f --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_18/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_18/train", + "rows": 5681, + "lengths_sample_mean_old": 3370.67, + "lengths_sample_mean_new": 4842.67, + "timestamp": "2026-05-11T15:39:06" +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow new file mode 100644 index 0000000000000000000000000000000000000000..ea32c36dc437b345a6759230bbb0f90b187c2d0e --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/data-00000-of-00001.arrow @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dcbf64278ed2036ebef6b5fe8fcabef18b25655206e27e471495c4d1436d48e +size 7830288 diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/dataset_info.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/dataset_info.json new file mode 100644 index 0000000000000000000000000000000000000000..51324591261cbedeaab4bf3cae73c0469c97e026 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/dataset_info.json @@ -0,0 +1,60 @@ +{ + "builder_name": "json", + "citation": "", + "config_name": "default", + "dataset_name": "json", + "dataset_size": 7441014, + "description": "", + "download_checksums": { + "/share/m2v_intern_v3/wangjunjie09/model_cache/VisionEncoder/ms-swift-data/video_sft_chunks_local/chunk_19.json": { + "num_bytes": 8427096, + "checksum": null + } + }, + "download_size": 8427096, + "features": { + "messages": [ + { + "content": { + "dtype": "string", + "_type": "Value" + }, + "role": { + "dtype": "string", + "_type": "Value" + } + } + ], + "videos": { + "feature": { + "dtype": "string", + "_type": "Value" + }, + "_type": "Sequence" + }, + "lengths": { + "feature": { + "dtype": "int64", + "_type": "Value" + }, + "_type": "Sequence" + } + }, + "homepage": "", + "license": "", + "size_in_bytes": 15868110, + "splits": { + "train": { + "name": "train", + "num_bytes": 7441014, + "num_examples": 5676, + "dataset_name": "json" + } + }, + "version": { + "version_str": "0.0.0", + "major": 0, + "minor": 0, + "patch": 0 + } +} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/state.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/state.json new file mode 100644 index 0000000000000000000000000000000000000000..1f62fa1f9e617c9d3a80f4e625e766e746898a18 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/state.json @@ -0,0 +1 @@ +{"_data_files": [{"filename": "data-00000-of-00001.arrow"}], "_fingerprint": "3802f4b9491a82c2", "_format_columns": null, "_format_kwargs": {}, "_format_type": null, "_output_all_columns": false, "_split": null} \ No newline at end of file diff --git a/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/vjepa21_patch_meta.json b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/vjepa21_patch_meta.json new file mode 100644 index 0000000000000000000000000000000000000000..5e4094adc569c7850e3ec31f43d8a0c365afd123 --- /dev/null +++ b/vmllm_cached/vjepa21/video_10pct_chunks/chunk_19/train/vjepa21_patch_meta.json @@ -0,0 +1,12 @@ +{ + "patcher": "siglip2_to_vjepa21", + "mode": "video", + "from": "siglip2 (SigLIP2 base 16f \u00d7 196 + 1 = 3137 video tokens)", + "to": "vjepa21 (V-JEPA 2.1 16f \u00d7 288 + 1 = 4609 video tokens)", + "delta_formula": "lengths[0] += 1472 * len(videos)", + "input": "/share/m2v_intern_v3/wangjunjie09/VisionEncoder/data/vmllm_cached/siglip2/video_10pct_chunks/chunk_19/train", + "rows": 5676, + "lengths_sample_mean_old": 3396.02, + "lengths_sample_mean_new": 4868.02, + "timestamp": "2026-05-11T15:39:07" +} \ No newline at end of file