Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 llava_vqa_judge_grpo_local_qwen3/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 llava_vqa_judge_grpo_local_qwen3_new_1epoch/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_30/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1_2026-03-31_18-23-55.log filter=lfs diff=lfs merge=lfs -text

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b16d86252a04c84cea641a4f5a57b9abf26a189c57145c92c5d8c9c21608a05
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b12150881d1c4a3c4a212bdd503c8ae6bb6b015a9b0ec3b94b3346fae1aecb2a
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab917eca73cbbe9dc02e9c86f7f60c96163cd55ef8c9ad57014404468f10b7a
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdbcf04e75d1b3df41f80930ea503336d8af3e8030050b94efd6f46a1f6381d
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77b8a5759d8117bb602706949f672bb63b7a88de47df3c0067c811a5e4d118a
+size 15205

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9cc184d2be40f9ab11dbaf5898491da1b28daec26f6dcb596a4516340901db
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfe8162fe2d1e28b3e1a61d33f6eef535213e447416566a131933bdf63d9f8d5
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/extra_state_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:befb575db58c6b645eb271b4df127ad5dfc6df8b67546cb1ae5b97fa0a281359
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 8
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "../ckpts/Qwen2.5-VL-7B-Instruct",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float32",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.57.1"
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/huggingface/video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": false,
+  "fps": null,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_frames": 4,
+  "min_pixels": 3136,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen2VLVideoProcessor"
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea3bebc626a4a321c35a328405f45940a789e7ba2a3bbdede1e1122dfa160d8
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743d4672211f853367279067a68266e2406da1e4f5595eedde4629d62930e088
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49be464c16f889185e258e3223be4230e546db1a933bcfc240d1d50b2734038a
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb95504f160b3a27781f54365ecbb5dc8ba0aa7cfce02663e3e5f8535b9ebf6
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d96915ca2094912e26fe711aac11846592a2575a39faaaca70e783a8a109c0
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84449eaccbbbd9d0c1964e1bde8022d4036da1d02847f18737323fa70abbc7d2
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526d0dbb04794f0d28da13fede71369b0f57d79ba6a20a2af33964ac62a4cd21
+size 4146658699

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/model_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0643343f719f29bfb44575df7011ac437418eb56c279152902410933e26740d
+size 4145343883

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de66d673e52dd90865f1ca539b957b15b36c4110d13e4caec7f030df57b849a6
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37a831c7dd0ac0a12aed03af9856fbc15dc4c1faaf1d3132c3475124e6357625
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61146fc533549efab8358dfd938b18d81ae5b0d8db77aa5bfc6e8af0ec6ff459
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1106d0f9aa4cc78f19d006f3b7bdc373698f0a8f9d8b065ea667d252fabd2946
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339c6fecabc4710a351ec9a926d1f30d122e1b7c12e117ff69e294744be84952
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02895a5904001fe9f3b4c1a7cdf89034eea3f3a106e06bd5b3ab80ed135deb9e
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d36304ac4f280a8229aef6e02ebf24ff594c05a9dbc25034eb43732f6ee857
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/actor/optim_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fe4f7af1dc19db95ebc9e0cb4a5c3956a732c8b2ff28f185570134f101d506
+size 8292331679

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_10/data.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9fd9f4dd1e1bac1f0caab81813e6f5e02b8141eef28574e7efcf9dfa077c0d3
+size 7316

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfafebb094f5c699cbaf7fcab36c6f1237bd115a7fbecc497ff56bb2ba3ece13
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30dd178771a2aedac938ee7eb4668a425c9fd6dba24c03b5f3379d2fc1bc1d11
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bad2d440fefdd55b126fcd8487ad2cfb24fbd5d9b8a20bde8524b951a77b40
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_3.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd493d754fe600a62c03d5432ee3bb94b522cc7fc6fcd9ec5b8ca49d352c64a2
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_4.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75c85d3023ed95eb71f0ba1fbb294d4346508b2a80ab2246a03505eec87bde5
+size 15205

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_5.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee186ca62005ac0f710b77eabf643516b284594af4183aadda5f9c54b2256345
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_6.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8280c5ff59fadd3d12bbdb130a58b4eebd7369ac0d287e112499a549dcad2040
+size 15141

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/extra_state_world_size_8_rank_7.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc6be9b7353f24a752fe76a5815bc7df1361fe0a81127f5f9c23add32110cf6
+size 15077

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 8
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/huggingface/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/huggingface/chat_template.jinja

@@ -0,0 +1,7 @@
+{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
+You are a helpful assistant.<|im_end|>
+{% endif %}<|im_start|>{{ message['role'] }}
+{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
+{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
+{% endif %}

grpo_Qwen2.5-VL-7B-Instruct_tr1024_mini256_micro32_n8_lr5e-6_cosine_ep1/global_step_20/actor/huggingface/config.json

@@ -0,0 +1,132 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 28,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "text_config": {
+    "_name_or_path": "../ckpts/Qwen2.5-VL-7B-Instruct",
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "layer_types": [
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 128000,
+    "max_window_layers": 28,
+    "model_type": "qwen2_5_vl_text",
+    "num_attention_heads": 28,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_section": [
+        16,
+        24,
+        24
+      ],
+      "rope_type": "default",
+      "type": "default"
+    },
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vision_token_id": 151654,
+    "vocab_size": 152064
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "dtype": "float32",
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 3584,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}