Add checkpoint-100

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-100/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
+}

checkpoint-100/chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

checkpoint-100/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/mmu-vcg-hdd/multimodal/models/Qwen2.5-VL-7B-Instruct",
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "hidden_size": 1280,
+    "in_chans": 3,
+    "model_type": "qwen2_5_vl",
+    "spatial_patch_size": 14,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16"
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 152064
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.1,
+  "top_k": 1,
+  "top_p": 0.001,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

checkpoint-100/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5a4fee73ec78254fff1fdbf4d08d96359e7ab2585bb239e3ba577f92103c4e
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2859657594be16ae024990d102fe6b906fd5af90bf7cdad459865904aa4ea43
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da90ecb3d284c68315991ec6f0bad0ce13d6dc611be4c295321e142d02e9cb63
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5e73df0c438d890bcb0ee39e984ee4d100ed294870290bb1b151ceaa9d54cef
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c512b3436ff640d4e67cabc85404baa365bd960ca081ac163e47fd1948e14073
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78af9b5c2283792f741c46a836b7d38187cbd085bd0af2e27c750e85f4101612
+size 14215152126

checkpoint-100/global_step100/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140081d25dc9c4a7973f3ab7e19f8d8c5228f9007ebbadbfde1da1b5751c4a63
+size 14215152126

checkpoint-100/global_step100/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ef289a60d9e56e23d1ef010af826201601e88870684662bc0f6e62e0964a52
+size 349379

checkpoint-100/global_step100/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e8528fb83a210e8bbd9a1781ab61e6e2dccf62c195bbffe29b3f5d19f621f3
+size 349379

checkpoint-100/global_step100/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fdccf46cd71e8cd9940d81e40bbead8c4a0682b4ce5eb0adad5b7da517f633
+size 349379

checkpoint-100/global_step100/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96302f8de00f370807a0d10a4b9692ce083f2dc63ba7ff3971b8a7552fd372ff
+size 349379

checkpoint-100/global_step100/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c566d74345baaaff9ef6bdae4e29805a0c70ce8d73d9f035c9b64b6197eaef
+size 349379

checkpoint-100/global_step100/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1ee97740ed83770c6aaf4053f6df9be408c00d16f51acaba3c594905b022d9
+size 349379

checkpoint-100/global_step100/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98650274726f869a3919c807f40b164a18fb039505e1dcc8bf1af72a4df56cd3
+size 349379

checkpoint-100/latest

@@ -0,0 +1 @@
+global_step100

checkpoint-100/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c949456a2a5daf040cbb7fa6d5e69a8e09b5b15e8c7947e30813abcebcc9a5a
+size 4968243304

checkpoint-100/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c122a861d6f237c400fb37ee991eb7b3a5ecfba2e37fd66052ca075928ce4659
+size 4991495816

checkpoint-100/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5b808ac1a1d9c503b68a86f1a68bde9fc6aee75d59a03ea6230a783cfbc18a
+size 4932751040

checkpoint-100/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84db3aa9bc8da83ff4bbb8a194a62906895de55a2999dce7d2c5d288973ed194
+size 1691924384

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,736 @@
+{
+  "metadata": {
+    "total_size": 16584333312
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00004.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00004.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors"
+  }
+}

checkpoint-100/preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2_5_VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 501760,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f104c0a59bdc20c25c610ef4c0ff6538f117f140b0a699849a44b26df8bda3
+size 15920

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d84197aa3be5cfd6682a1492c0d1fd1d3ba9173df4e8017692d655ceb125cd8
+size 15984

checkpoint-100/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb994fd4b929ea5c3efcb2f8f283afb00b340c578cf9743e94d598bd703fe0ef
+size 15984

checkpoint-100/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b226fc74b06589ef08b4fcbca3ae21bd4ae1448e0ae8748c1d089c1b97974d7
+size 15984

checkpoint-100/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da8cef64270987f1c3235c501c52c498ff923e3cf41d43936a4b9e69275eb78
+size 15984

checkpoint-100/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0236f0f37d60047ab89129a3f187ccd4ff0ceeefd93999f017ee20ff5f32047a
+size 15984

checkpoint-100/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168acd414a1c9e5c5d391d2afd670df4ee0b5fbb787b1f038d26d879de338fdf
+size 15984

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962045a800a4761bc19c4ebf5ee3c6890e84ba3464ae01d9b9dce70cf6240a93
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "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
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,1633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.007071635669330316,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 200.10714721679688,
+      "epoch": 7.071635669330315e-05,
+      "grad_norm": 4.679907559144155,
+      "kl": 0.0,
+      "learning_rate": 9.999961446907352e-07,
+      "loss": -0.0,
+      "reward": 1.4622538089752197,
+      "reward_std": 0.3791443407535553,
+      "rewards/accuracy_reward": 0.590825080871582,
+      "rewards/format_reward": 0.6875000596046448,
+      "step": 1,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 247.7857208251953,
+      "epoch": 0.0001414327133866063,
+      "grad_norm": 2.6934508684924126,
+      "kl": 0.000797271728515625,
+      "learning_rate": 9.999845788223948e-07,
+      "loss": 0.0,
+      "reward": 1.0509984493255615,
+      "reward_std": 0.29602327942848206,
+      "rewards/accuracy_reward": 0.28671279549598694,
+      "rewards/format_reward": 0.7142857313156128,
+      "step": 2,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 307.76788330078125,
+      "epoch": 0.00021214907007990948,
+      "grad_norm": 3.276748844204242,
+      "kl": 0.000743865966796875,
+      "learning_rate": 9.999653025733385e-07,
+      "loss": 0.0,
+      "reward": 1.1041209697723389,
+      "reward_std": 0.5020884275436401,
+      "rewards/accuracy_reward": 0.3005495071411133,
+      "rewards/format_reward": 0.6875000596046448,
+      "step": 3,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 268.7321472167969,
+      "epoch": 0.0002828654267732126,
+      "grad_norm": 2.9704401115092747,
+      "kl": 0.00119781494140625,
+      "learning_rate": 9.999383162408303e-07,
+      "loss": 0.0,
+      "reward": 1.0085241794586182,
+      "reward_std": 0.4387863874435425,
+      "rewards/accuracy_reward": 0.2245955765247345,
+      "rewards/format_reward": 0.7053571939468384,
+      "step": 4,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 253.75001525878906,
+      "epoch": 0.0003535817834665158,
+      "grad_norm": 2.166698944690136,
+      "kl": 0.00182342529296875,
+      "learning_rate": 9.999036202410323e-07,
+      "loss": 0.0001,
+      "reward": 1.137129545211792,
+      "reward_std": 0.24109232425689697,
+      "rewards/accuracy_reward": 0.2549867331981659,
+      "rewards/format_reward": 0.8392857313156128,
+      "step": 5,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 292.3214416503906,
+      "epoch": 0.00042429814015981895,
+      "grad_norm": 1.7828370646905003,
+      "kl": 0.001983642578125,
+      "learning_rate": 9.998612151090002e-07,
+      "loss": 0.0001,
+      "reward": 1.260791301727295,
+      "reward_std": 0.23829373717308044,
+      "rewards/accuracy_reward": 0.3715055584907532,
+      "rewards/format_reward": 0.8750000596046448,
+      "step": 6,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 250.71429443359375,
+      "epoch": 0.0004950144968531221,
+      "grad_norm": 2.0183775912817064,
+      "kl": 0.004669189453125,
+      "learning_rate": 9.998111014986734e-07,
+      "loss": 0.0002,
+      "reward": 1.1892523765563965,
+      "reward_std": 0.28430700302124023,
+      "rewards/accuracy_reward": 0.2874666750431061,
+      "rewards/format_reward": 0.8839285969734192,
+      "step": 7,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 254.8035888671875,
+      "epoch": 0.0005657308535464252,
+      "grad_norm": 14.87774889660559,
+      "kl": 0.00372314453125,
+      "learning_rate": 9.997532801828658e-07,
+      "loss": 0.0001,
+      "reward": 1.4599319696426392,
+      "reward_std": 0.3439008295536041,
+      "rewards/accuracy_reward": 0.40457478165626526,
+      "rewards/format_reward": 0.973214328289032,
+      "step": 8,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 232.44644165039062,
+      "epoch": 0.0006364472102397285,
+      "grad_norm": 2.692129500093887,
+      "kl": 0.0035400390625,
+      "learning_rate": 9.996877520532534e-07,
+      "loss": 0.0001,
+      "reward": 1.3368793725967407,
+      "reward_std": 0.1027989462018013,
+      "rewards/accuracy_reward": 0.31009361147880554,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 9,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 286.7321472167969,
+      "epoch": 0.0007071635669330316,
+      "grad_norm": 3.031406131634961,
+      "kl": 0.00543212890625,
+      "learning_rate": 9.996145181203615e-07,
+      "loss": 0.0002,
+      "reward": 1.3317698240280151,
+      "reward_std": 0.20930121839046478,
+      "rewards/accuracy_reward": 0.2996269762516022,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 10,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 195.62501525878906,
+      "epoch": 0.0007778799236263348,
+      "grad_norm": 3.12633601275179,
+      "kl": 0.005401611328125,
+      "learning_rate": 9.995335795135475e-07,
+      "loss": 0.0002,
+      "reward": 1.6218074560165405,
+      "reward_std": 0.08352632075548172,
+      "rewards/accuracy_reward": 0.45216456055641174,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 11,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 160.71429443359375,
+      "epoch": 0.0008485962803196379,
+      "grad_norm": 2.0480927531546067,
+      "kl": 0.00927734375,
+      "learning_rate": 9.99444937480985e-07,
+      "loss": 0.0004,
+      "reward": 1.4629789590835571,
+      "reward_std": 0.17699524760246277,
+      "rewards/accuracy_reward": 0.4861932098865509,
+      "rewards/format_reward": 0.973214328289032,
+      "step": 12,
+      "temporal_rewards": 0.4285714328289032
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 266.375,
+      "epoch": 0.0009193126370129411,
+      "grad_norm": 5.805064528423736,
+      "kl": 0.00897216796875,
+      "learning_rate": 9.993485933896437e-07,
+      "loss": 0.0004,
+      "reward": 1.501465916633606,
+      "reward_std": 0.2271209955215454,
+      "rewards/accuracy_reward": 0.30503714084625244,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 13,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 222.69644165039062,
+      "epoch": 0.0009900289937062442,
+      "grad_norm": 5.728015554738999,
+      "kl": 0.01397705078125,
+      "learning_rate": 9.99244548725269e-07,
+      "loss": 0.0006,
+      "reward": 1.4509989023208618,
+      "reward_std": 0.3031184673309326,
+      "rewards/accuracy_reward": 0.4188559651374817,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 14,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 247.1428680419922,
+      "epoch": 0.0010607453503995474,
+      "grad_norm": 2.4169757843226214,
+      "kl": 0.0179443359375,
+      "learning_rate": 9.99132805092358e-07,
+      "loss": 0.0007,
+      "reward": 1.1342699527740479,
+      "reward_std": 0.09272795170545578,
+      "rewards/accuracy_reward": 0.08069846034049988,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 15,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 280.83929443359375,
+      "epoch": 0.0011314617070928505,
+      "grad_norm": 2.280721411483325,
+      "kl": 0.01025390625,
+      "learning_rate": 9.990133642141357e-07,
+      "loss": 0.0004,
+      "reward": 1.4930970668792725,
+      "reward_std": 0.1474475860595703,
+      "rewards/accuracy_reward": 0.4930969774723053,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 16,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 204.37501525878906,
+      "epoch": 0.0012021780637861538,
+      "grad_norm": 2.937458054420694,
+      "kl": 0.01165771484375,
+      "learning_rate": 9.988862279325284e-07,
+      "loss": 0.0005,
+      "reward": 1.2890753746032715,
+      "reward_std": 0.1806221753358841,
+      "rewards/accuracy_reward": 0.2426467388868332,
+      "rewards/format_reward": 1.0,
+      "step": 17,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 294.6071472167969,
+      "epoch": 0.001272894420479457,
+      "grad_norm": 4.963302285754617,
+      "kl": 0.0174560546875,
+      "learning_rate": 9.98751398208135e-07,
+      "loss": 0.0007,
+      "reward": 1.1960500478744507,
+      "reward_std": 0.18731099367141724,
+      "rewards/accuracy_reward": 0.24247848987579346,
+      "rewards/format_reward": 0.8660714626312256,
+      "step": 18,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 205.57144165039062,
+      "epoch": 0.00134361077717276,
+      "grad_norm": 2.584688524236813,
+      "kl": 0.015380859375,
+      "learning_rate": 9.986088771201963e-07,
+      "loss": 0.0006,
+      "reward": 1.411386251449585,
+      "reward_std": 0.1405026614665985,
+      "rewards/accuracy_reward": 0.4221004843711853,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 19,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 243.0535888671875,
+      "epoch": 0.0014143271338660631,
+      "grad_norm": 8.371430451495444,
+      "kl": 0.01507568359375,
+      "learning_rate": 9.98458666866564e-07,
+      "loss": 0.0006,
+      "reward": 1.3473149538040161,
+      "reward_std": 0.20817457139492035,
+      "rewards/accuracy_reward": 0.2723149061203003,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 20,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 260.5714416503906,
+      "epoch": 0.0014850434905593665,
+      "grad_norm": 2.70051006406536,
+      "kl": 0.0142822265625,
+      "learning_rate": 9.983007697636658e-07,
+      "loss": 0.0006,
+      "reward": 1.2491365671157837,
+      "reward_std": 0.2304382622241974,
+      "rewards/accuracy_reward": 0.22592230141162872,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 21,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 263.7857360839844,
+      "epoch": 0.0015557598472526696,
+      "grad_norm": 3.2825417374567896,
+      "kl": 0.017578125,
+      "learning_rate": 9.981351882464707e-07,
+      "loss": 0.0007,
+      "reward": 1.2244305610656738,
+      "reward_std": 0.25213029980659485,
+      "rewards/accuracy_reward": 0.2208590805530548,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 22,
+      "temporal_rewards": 0.4285714328289032
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 305.9464416503906,
+      "epoch": 0.0016264762039459727,
+      "grad_norm": 2.925214630091263,
+      "kl": 0.00799560546875,
+      "learning_rate": 9.979619248684501e-07,
+      "loss": 0.0003,
+      "reward": 1.4240540266036987,
+      "reward_std": 0.29196304082870483,
+      "rewards/accuracy_reward": 0.43298259377479553,
+      "rewards/format_reward": 0.8928571939468384,
+      "step": 23,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 289.51788330078125,
+      "epoch": 0.0016971925606392758,
+      "grad_norm": 2.912269631441271,
+      "kl": 0.0130615234375,
+      "learning_rate": 9.9778098230154e-07,
+      "loss": 0.0005,
+      "reward": 1.4945178031921387,
+      "reward_std": 0.12553724646568298,
+      "rewards/accuracy_reward": 0.3159463107585907,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 24,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 205.37501525878906,
+      "epoch": 0.001767908917332579,
+      "grad_norm": 3.443548590018792,
+      "kl": 0.0238037109375,
+      "learning_rate": 9.975923633360984e-07,
+      "loss": 0.001,
+      "reward": 1.3629069328308105,
+      "reward_std": 0.21605005860328674,
+      "rewards/accuracy_reward": 0.33790692687034607,
+      "rewards/format_reward": 1.0,
+      "step": 25,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 314.21429443359375,
+      "epoch": 0.0018386252740258823,
+      "grad_norm": 2.528502389328177,
+      "kl": 0.0145263671875,
+      "learning_rate": 9.973960708808631e-07,
+      "loss": 0.0006,
+      "reward": 1.4366943836212158,
+      "reward_std": 0.25942346453666687,
+      "rewards/accuracy_reward": 0.32062289118766785,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 26,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 268.7857360839844,
+      "epoch": 0.0019093416307191854,
+      "grad_norm": 4.350357161622448,
+      "kl": 0.011474609375,
+      "learning_rate": 9.971921079629069e-07,
+      "loss": 0.0005,
+      "reward": 1.3468642234802246,
+      "reward_std": 0.11351645737886429,
+      "rewards/accuracy_reward": 0.22543567419052124,
+      "rewards/format_reward": 1.0,
+      "step": 27,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 293.46429443359375,
+      "epoch": 0.0019800579874124885,
+      "grad_norm": 4.010526453910769,
+      "kl": 0.009765625,
+      "learning_rate": 9.969804777275898e-07,
+      "loss": 0.0004,
+      "reward": 1.3793425559997559,
+      "reward_std": 0.19644470512866974,
+      "rewards/accuracy_reward": 0.37219956517219543,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 28,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 247.8928680419922,
+      "epoch": 0.0020507743441057916,
+      "grad_norm": 1.8705072948266848,
+      "kl": 0.00897216796875,
+      "learning_rate": 9.967611834385122e-07,
+      "loss": 0.0004,
+      "reward": 1.508015513420105,
+      "reward_std": 0.20669502019882202,
+      "rewards/accuracy_reward": 0.5080153346061707,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 29,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 259.25,
+      "epoch": 0.0021214907007990947,
+      "grad_norm": 4.328117926524593,
+      "kl": 0.00927734375,
+      "learning_rate": 9.965342284774631e-07,
+      "loss": 0.0004,
+      "reward": 1.474429965019226,
+      "reward_std": 0.11664658784866333,
+      "rewards/accuracy_reward": 0.3887157142162323,
+      "rewards/format_reward": 1.0,
+      "step": 30,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 244.10714721679688,
+      "epoch": 0.002192207057492398,
+      "grad_norm": 2.1832119295808825,
+      "kl": 0.01385498046875,
+      "learning_rate": 9.962996163443688e-07,
+      "loss": 0.0006,
+      "reward": 1.416548252105713,
+      "reward_std": 0.14642640948295593,
+      "rewards/accuracy_reward": 0.30047670006752014,
+      "rewards/format_reward": 1.0,
+      "step": 31,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.7142857142857143,
+      "all_wrong": 0.0,
+      "completion_length": 200.82144165039062,
+      "epoch": 0.002262923414185701,
+      "grad_norm": 1.4223202232999537,
+      "kl": 0.01397705078125,
+      "learning_rate": 9.960573506572389e-07,
+      "loss": 0.0006,
+      "reward": 1.930145502090454,
+      "reward_std": 0.12284065037965775,
+      "rewards/accuracy_reward": 0.8408597707748413,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 32,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 347.0714416503906,
+      "epoch": 0.0023336397708790045,
+      "grad_norm": 3.518686828892219,
+      "kl": 0.006744384765625,
+      "learning_rate": 9.958074351521096e-07,
+      "loss": 0.0003,
+      "reward": 1.259355068206787,
+      "reward_std": 0.2953766882419586,
+      "rewards/accuracy_reward": 0.22899788618087769,
+      "rewards/format_reward": 0.973214328289032,
+      "step": 33,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 292.125,
+      "epoch": 0.0024043561275723076,
+      "grad_norm": 7.331431973368505,
+      "kl": 0.0089111328125,
+      "learning_rate": 9.955498736829874e-07,
+      "loss": 0.0004,
+      "reward": 1.4256235361099243,
+      "reward_std": 0.2976904809474945,
+      "rewards/accuracy_reward": 0.4613378047943115,
+      "rewards/format_reward": 0.9375000596046448,
+      "step": 34,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 303.125,
+      "epoch": 0.0024750724842656107,
+      "grad_norm": 9.691249760972333,
+      "kl": 0.00848388671875,
+      "learning_rate": 9.952846702217885e-07,
+      "loss": 0.0003,
+      "reward": 1.3373116254806519,
+      "reward_std": 0.19856014847755432,
+      "rewards/accuracy_reward": 0.22838297486305237,
+      "rewards/format_reward": 1.0,
+      "step": 35,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 250.48214721679688,
+      "epoch": 0.002545788840958914,
+      "grad_norm": 2.993544004162704,
+      "kl": 0.012939453125,
+      "learning_rate": 9.950118288582787e-07,
+      "loss": 0.0005,
+      "reward": 1.450445294380188,
+      "reward_std": 0.23749849200248718,
+      "rewards/accuracy_reward": 0.4183023273944855,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 36,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 177.00001525878906,
+      "epoch": 0.002616505197652217,
+      "grad_norm": 2.147613846896577,
+      "kl": 0.01483154296875,
+      "learning_rate": 9.947313538000092e-07,
+      "loss": 0.0006,
+      "reward": 1.5246427059173584,
+      "reward_std": 0.15763144195079803,
+      "rewards/accuracy_reward": 0.5139283537864685,
+      "rewards/format_reward": 1.0,
+      "step": 37,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 229.58929443359375,
+      "epoch": 0.00268722155434552,
+      "grad_norm": 1.9805499967733886,
+      "kl": 0.01519775390625,
+      "learning_rate": 9.944432493722524e-07,
+      "loss": 0.0006,
+      "reward": 1.3561514616012573,
+      "reward_std": 0.1405426561832428,
+      "rewards/accuracy_reward": 0.31329435110092163,
+      "rewards/format_reward": 1.0,
+      "step": 38,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 344.0535888671875,
+      "epoch": 0.002757937911038823,
+      "grad_norm": 1.6211008791444943,
+      "kl": 0.0111083984375,
+      "learning_rate": 9.941475200179346e-07,
+      "loss": 0.0004,
+      "reward": 1.3877519369125366,
+      "reward_std": 0.082041434943676,
+      "rewards/accuracy_reward": 0.32525181770324707,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 39,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 322.71429443359375,
+      "epoch": 0.0028286542677321263,
+      "grad_norm": 1.9545000376681727,
+      "kl": 0.0096435546875,
+      "learning_rate": 9.938441702975689e-07,
+      "loss": 0.0004,
+      "reward": 1.4263824224472046,
+      "reward_std": 0.1756214201450348,
+      "rewards/accuracy_reward": 0.3406681418418884,
+      "rewards/format_reward": 1.0,
+      "step": 40,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 314.3035888671875,
+      "epoch": 0.0028993706244254294,
+      "grad_norm": 2.053784837086962,
+      "kl": 0.0103759765625,
+      "learning_rate": 9.935332048891826e-07,
+      "loss": 0.0004,
+      "reward": 1.521074652671814,
+      "reward_std": 0.1329503059387207,
+      "rewards/accuracy_reward": 0.4103603959083557,
+      "rewards/format_reward": 1.0,
+      "step": 41,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 360.2321472167969,
+      "epoch": 0.002970086981118733,
+      "grad_norm": 2.2804514926564057,
+      "kl": 0.0103759765625,
+      "learning_rate": 9.932146285882476e-07,
+      "loss": 0.0004,
+      "reward": 1.397080898284912,
+      "reward_std": 0.15315495431423187,
+      "rewards/accuracy_reward": 0.2845808267593384,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 42,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 321.8214416503906,
+      "epoch": 0.003040803337812036,
+      "grad_norm": 1.992676290215063,
+      "kl": 0.0155029296875,
+      "learning_rate": 9.928884463076043e-07,
+      "loss": 0.0006,
+      "reward": 1.3467375040054321,
+      "reward_std": 0.16957923769950867,
+      "rewards/accuracy_reward": 0.24138039350509644,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 43,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 340.1607360839844,
+      "epoch": 0.003111519694505339,
+      "grad_norm": 2.003574826398129,
+      "kl": 0.0164794921875,
+      "learning_rate": 9.925546630773868e-07,
+      "loss": 0.0007,
+      "reward": 1.2990601062774658,
+      "reward_std": 0.1996757686138153,
+      "rewards/accuracy_reward": 0.3044171929359436,
+      "rewards/format_reward": 0.8660714626312256,
+      "step": 44,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 378.5535888671875,
+      "epoch": 0.0031822360511986423,
+      "grad_norm": 1.5251934336406172,
+      "kl": 0.0140380859375,
+      "learning_rate": 9.922132840449458e-07,
+      "loss": 0.0006,
+      "reward": 1.2783958911895752,
+      "reward_std": 0.14688079059123993,
+      "rewards/accuracy_reward": 0.16768160462379456,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 45,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 385.89288330078125,
+      "epoch": 0.0032529524078919454,
+      "grad_norm": 5.043598020520579,
+      "kl": 0.01226806640625,
+      "learning_rate": 9.91864314474768e-07,
+      "loss": 0.0005,
+      "reward": 1.4317442178726196,
+      "reward_std": 0.13028410077095032,
+      "rewards/accuracy_reward": 0.29245835542678833,
+      "rewards/format_reward": 1.0,
+      "step": 46,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 429.64288330078125,
+      "epoch": 0.0033236687645852485,
+      "grad_norm": 1.5608232632837769,
+      "kl": 0.0081787109375,
+      "learning_rate": 9.915077597483958e-07,
+      "loss": 0.0003,
+      "reward": 1.2896418571472168,
+      "reward_std": 0.34282949566841125,
+      "rewards/accuracy_reward": 0.29678457975387573,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 47,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 369.7857360839844,
+      "epoch": 0.0033943851212785516,
+      "grad_norm": 1.3115904622960182,
+      "kl": 0.0103759765625,
+      "learning_rate": 9.911436253643443e-07,
+      "loss": 0.0004,
+      "reward": 1.4439650774002075,
+      "reward_std": 0.16484510898590088,
+      "rewards/accuracy_reward": 0.4296793043613434,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 48,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 359.1607360839844,
+      "epoch": 0.0034651014779718547,
+      "grad_norm": 1.8675624762178065,
+      "kl": 0.01116943359375,
+      "learning_rate": 9.907719169380162e-07,
+      "loss": 0.0004,
+      "reward": 1.3826886415481567,
+      "reward_std": 0.10018106549978256,
+      "rewards/accuracy_reward": 0.2291172444820404,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 49,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 260.0,
+      "epoch": 0.003535817834665158,
+      "grad_norm": 1.7629184411875067,
+      "kl": 0.01507568359375,
+      "learning_rate": 9.90392640201615e-07,
+      "loss": 0.0006,
+      "reward": 1.2967737913131714,
+      "reward_std": 0.19944338500499725,
+      "rewards/accuracy_reward": 0.2610594630241394,
+      "rewards/format_reward": 1.0,
+      "step": 50,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 274.5357360839844,
+      "epoch": 0.0036065341913584614,
+      "grad_norm": 2.582277447707262,
+      "kl": 0.0167236328125,
+      "learning_rate": 9.900058010040577e-07,
+      "loss": 0.0007,
+      "reward": 1.432778239250183,
+      "reward_std": 0.27678585052490234,
+      "rewards/accuracy_reward": 0.35242101550102234,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 51,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 292.9464416503906,
+      "epoch": 0.0036772505480517645,
+      "grad_norm": 2.660184539699317,
+      "kl": 0.0234375,
+      "learning_rate": 9.89611405310883e-07,
+      "loss": 0.0009,
+      "reward": 1.4461818933486938,
+      "reward_std": 0.21560263633728027,
+      "rewards/accuracy_reward": 0.3622532784938812,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 52,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 247.9285888671875,
+      "epoch": 0.0037479669047450676,
+      "grad_norm": 2.348619995816532,
+      "kl": 0.02099609375,
+      "learning_rate": 9.8920945920416e-07,
+      "loss": 0.0008,
+      "reward": 1.6287018060684204,
+      "reward_std": 0.13119636476039886,
+      "rewards/accuracy_reward": 0.5001303553581238,
+      "rewards/format_reward": 1.0,
+      "step": 53,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 357.7500305175781,
+      "epoch": 0.0038186832614383708,
+      "grad_norm": 3.300186824637339,
+      "kl": 0.013916015625,
+      "learning_rate": 9.887999688823954e-07,
+      "loss": 0.0006,
+      "reward": 1.3542555570602417,
+      "reward_std": 0.08903272449970245,
+      "rewards/accuracy_reward": 0.29711267352104187,
+      "rewards/format_reward": 1.0,
+      "step": 54,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 285.6071472167969,
+      "epoch": 0.003889399618131674,
+      "grad_norm": 2.7314218605333624,
+      "kl": 0.016845703125,
+      "learning_rate": 9.883829406604361e-07,
+      "loss": 0.0007,
+      "reward": 1.2821252346038818,
+      "reward_std": 0.28221410512924194,
+      "rewards/accuracy_reward": 0.24998226761817932,
+      "rewards/format_reward": 1.0,
+      "step": 55,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 337.83929443359375,
+      "epoch": 0.003960115974824977,
+      "grad_norm": 1.5413615695610776,
+      "kl": 0.01397705078125,
+      "learning_rate": 9.879583809693736e-07,
+      "loss": 0.0006,
+      "reward": 1.3935561180114746,
+      "reward_std": 0.0765104740858078,
+      "rewards/accuracy_reward": 0.31498464941978455,
+      "rewards/format_reward": 1.0,
+      "step": 56,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 389.4821472167969,
+      "epoch": 0.0040308323315182805,
+      "grad_norm": 2.0151756007314714,
+      "kl": 0.01226806640625,
+      "learning_rate": 9.875262963564435e-07,
+      "loss": 0.0005,
+      "reward": 1.513351559638977,
+      "reward_std": 0.25552207231521606,
+      "rewards/accuracy_reward": 0.513351559638977,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 57,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 278.1785888671875,
+      "epoch": 0.004101548688211583,
+      "grad_norm": 1.9172194743179696,
+      "kl": 0.019287109375,
+      "learning_rate": 9.870866934849246e-07,
+      "loss": 0.0008,
+      "reward": 1.3478862047195435,
+      "reward_std": 0.20562618970870972,
+      "rewards/accuracy_reward": 0.3211003541946411,
+      "rewards/format_reward": 1.0,
+      "step": 58,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 374.6071472167969,
+      "epoch": 0.004172265044904887,
+      "grad_norm": 2.343462943955647,
+      "kl": 0.0166015625,
+      "learning_rate": 9.866395791340374e-07,
+      "loss": 0.0007,
+      "reward": 1.296674132347107,
+      "reward_std": 0.19219763576984406,
+      "rewards/accuracy_reward": 0.23953120410442352,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 59,
+      "temporal_rewards": 0.4285714328289032
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 342.1250305175781,
+      "epoch": 0.0042429814015981894,
+      "grad_norm": 4.637690517701243,
+      "kl": 0.01373291015625,
+      "learning_rate": 9.861849601988383e-07,
+      "loss": 0.0005,
+      "reward": 1.4211491346359253,
+      "reward_std": 0.1250295639038086,
+      "rewards/accuracy_reward": 0.4032919704914093,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 60,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 302.96429443359375,
+      "epoch": 0.004313697758291493,
+      "grad_norm": 1.9222617292615771,
+      "kl": 0.0262451171875,
+      "learning_rate": 9.857228436901134e-07,
+      "loss": 0.001,
+      "reward": 1.6846325397491455,
+      "reward_std": 0.21064738929271698,
+      "rewards/accuracy_reward": 0.5649893879890442,
+      "rewards/format_reward": 1.0,
+      "step": 61,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 305.75,
+      "epoch": 0.004384414114984796,
+      "grad_norm": 26.29906049647125,
+      "kl": 0.019287109375,
+      "learning_rate": 9.852532367342712e-07,
+      "loss": 0.0008,
+      "reward": 1.5550265312194824,
+      "reward_std": 0.32851195335388184,
+      "rewards/accuracy_reward": 0.4853835701942444,
+      "rewards/format_reward": 1.0,
+      "step": 62,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 259.2857360839844,
+      "epoch": 0.004455130471678099,
+      "grad_norm": 2.277143299225396,
+      "kl": 0.0250244140625,
+      "learning_rate": 9.847761465732316e-07,
+      "loss": 0.001,
+      "reward": 1.6335762739181519,
+      "reward_std": 0.16626587510108948,
+      "rewards/accuracy_reward": 0.48357629776000977,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 63,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 327.8214416503906,
+      "epoch": 0.004525846828371402,
+      "grad_norm": 1.8633049035565223,
+      "kl": 0.0167236328125,
+      "learning_rate": 9.842915805643156e-07,
+      "loss": 0.0007,
+      "reward": 1.2655143737792969,
+      "reward_std": 0.08168249577283859,
+      "rewards/accuracy_reward": 0.19765721261501312,
+      "rewards/format_reward": 1.0,
+      "step": 64,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 337.64288330078125,
+      "epoch": 0.0045965631850647054,
+      "grad_norm": 5.2839246810027305,
+      "kl": 0.0159912109375,
+      "learning_rate": 9.837995461801299e-07,
+      "loss": 0.0006,
+      "reward": 1.319211483001709,
+      "reward_std": 0.23389935493469238,
+      "rewards/accuracy_reward": 0.26921141147613525,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 65,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 274.9107360839844,
+      "epoch": 0.004667279541758009,
+      "grad_norm": 2.0489370067600152,
+      "kl": 0.0157470703125,
+      "learning_rate": 9.833000510084537e-07,
+      "loss": 0.0006,
+      "reward": 1.5802041292190552,
+      "reward_std": 0.32652613520622253,
+      "rewards/accuracy_reward": 0.4623468518257141,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 66,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 346.1071472167969,
+      "epoch": 0.004737995898451312,
+      "grad_norm": 2.9765363585370004,
+      "kl": 0.016845703125,
+      "learning_rate": 9.827931027521203e-07,
+      "loss": 0.0007,
+      "reward": 1.5119441747665405,
+      "reward_std": 0.13541929423809052,
+      "rewards/accuracy_reward": 0.4369440972805023,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 67,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 332.64288330078125,
+      "epoch": 0.004808712255144615,
+      "grad_norm": 2.0791874628611065,
+      "kl": 0.02001953125,
+      "learning_rate": 9.82278709228899e-07,
+      "loss": 0.0008,
+      "reward": 1.6526119709014893,
+      "reward_std": 0.16472205519676208,
+      "rewards/accuracy_reward": 0.48296913504600525,
+      "rewards/format_reward": 0.973214328289032,
+      "step": 68,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 314.6071472167969,
+      "epoch": 0.004879428611837918,
+      "grad_norm": 2.9259962040864806,
+      "kl": 0.0166015625,
+      "learning_rate": 9.817568783713743e-07,
+      "loss": 0.0007,
+      "reward": 1.376184105873108,
+      "reward_std": 0.15327244997024536,
+      "rewards/accuracy_reward": 0.2404698133468628,
+      "rewards/format_reward": 1.0,
+      "step": 69,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 429.2321472167969,
+      "epoch": 0.0049501449685312214,
+      "grad_norm": 1.4543069927272658,
+      "kl": 0.00872802734375,
+      "learning_rate": 9.812276182268236e-07,
+      "loss": 0.0003,
+      "reward": 1.4265930652618408,
+      "reward_std": 0.1878514438867569,
+      "rewards/accuracy_reward": 0.35337868332862854,
+      "rewards/format_reward": 0.973214328289032,
+      "step": 70,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 319.9464416503906,
+      "epoch": 0.005020861325224524,
+      "grad_norm": 2.8833448599523903,
+      "kl": 0.022216796875,
+      "learning_rate": 9.80690936957093e-07,
+      "loss": 0.0009,
+      "reward": 1.1564468145370483,
+      "reward_std": 0.14011871814727783,
+      "rewards/accuracy_reward": 0.09930393099784851,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 71,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 262.08929443359375,
+      "epoch": 0.005091577681917828,
+      "grad_norm": 2.9250018918381016,
+      "kl": 0.0196533203125,
+      "learning_rate": 9.801468428384716e-07,
+      "loss": 0.0008,
+      "reward": 1.4391757249832153,
+      "reward_std": 0.22654646635055542,
+      "rewards/accuracy_reward": 0.4248898923397064,
+      "rewards/format_reward": 1.0,
+      "step": 72,
+      "temporal_rewards": 0.4285714328289032
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 255.33929443359375,
+      "epoch": 0.00516229403861113,
+      "grad_norm": 2.757906287941002,
+      "kl": 0.0169677734375,
+      "learning_rate": 9.795953442615637e-07,
+      "loss": 0.0007,
+      "reward": 1.2926268577575684,
+      "reward_std": 0.13662691414356232,
+      "rewards/accuracy_reward": 0.21405534446239471,
+      "rewards/format_reward": 1.0,
+      "step": 73,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 280.96429443359375,
+      "epoch": 0.005233010395304434,
+      "grad_norm": 1.9114265067788339,
+      "kl": 0.0135498046875,
+      "learning_rate": 9.790364497311595e-07,
+      "loss": 0.0005,
+      "reward": 1.473499059677124,
+      "reward_std": 0.24891799688339233,
+      "rewards/accuracy_reward": 0.44849908351898193,
+      "rewards/format_reward": 1.0,
+      "step": 74,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 333.9821472167969,
+      "epoch": 0.0053037267519977374,
+      "grad_norm": 4.373657761893615,
+      "kl": 0.01263427734375,
+      "learning_rate": 9.784701678661044e-07,
+      "loss": 0.0005,
+      "reward": 1.6830004453659058,
+      "reward_std": 0.251014769077301,
+      "rewards/accuracy_reward": 0.5490719079971313,
+      "rewards/format_reward": 1.0,
+      "step": 75,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 187.44644165039062,
+      "epoch": 0.00537444310869104,
+      "grad_norm": 2.543487512106903,
+      "kl": 0.02392578125,
+      "learning_rate": 9.77896507399165e-07,
+      "loss": 0.001,
+      "reward": 1.6778168678283691,
+      "reward_std": 0.12846630811691284,
+      "rewards/accuracy_reward": 0.667102575302124,
+      "rewards/format_reward": 1.0,
+      "step": 76,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 301.625,
+      "epoch": 0.005445159465384344,
+      "grad_norm": 5.5479936200907884,
+      "kl": 0.01708984375,
+      "learning_rate": 9.773154771768955e-07,
+      "loss": 0.0007,
+      "reward": 1.2718242406845093,
+      "reward_std": 0.3140626549720764,
+      "rewards/accuracy_reward": 0.20932413637638092,
+      "rewards/format_reward": 0.9910714626312256,
+      "step": 77,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 367.08929443359375,
+      "epoch": 0.005515875822077646,
+      "grad_norm": 2.3377141382093547,
+      "kl": 0.01287841796875,
+      "learning_rate": 9.767270861595004e-07,
+      "loss": 0.0005,
+      "reward": 1.3282794952392578,
+      "reward_std": 0.20793180167675018,
+      "rewards/accuracy_reward": 0.21399372816085815,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 78,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 314.9107360839844,
+      "epoch": 0.00558659217877095,
+      "grad_norm": 3.975000609910864,
+      "kl": 0.0174560546875,
+      "learning_rate": 9.761313434206977e-07,
+      "loss": 0.0007,
+      "reward": 1.4134036302566528,
+      "reward_std": 0.11728669703006744,
+      "rewards/accuracy_reward": 0.4776892066001892,
+      "rewards/format_reward": 0.8571429252624512,
+      "step": 79,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 290.0535888671875,
+      "epoch": 0.005657308535464253,
+      "grad_norm": 46.026920138320996,
+      "kl": 0.015380859375,
+      "learning_rate": 9.755282581475767e-07,
+      "loss": 0.0006,
+      "reward": 1.3587440252304077,
+      "reward_std": 0.2508980929851532,
+      "rewards/accuracy_reward": 0.3730297386646271,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 80,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 343.51788330078125,
+      "epoch": 0.005728024892157556,
+      "grad_norm": 1.7806344788497834,
+      "kl": 0.01422119140625,
+      "learning_rate": 9.749178396404588e-07,
+      "loss": 0.0006,
+      "reward": 1.479040265083313,
+      "reward_std": 0.15753905475139618,
+      "rewards/accuracy_reward": 0.4147545397281647,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 81,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 234.94644165039062,
+      "epoch": 0.005798741248850859,
+      "grad_norm": 1.4240333944645842,
+      "kl": 0.0172119140625,
+      "learning_rate": 9.743000973127523e-07,
+      "loss": 0.0007,
+      "reward": 1.2428573369979858,
+      "reward_std": 0.2260817587375641,
+      "rewards/accuracy_reward": 0.2250000238418579,
+      "rewards/format_reward": 1.0,
+      "step": 82,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 201.85714721679688,
+      "epoch": 0.005869457605544162,
+      "grad_norm": 1.9441682237202011,
+      "kl": 0.0250244140625,
+      "learning_rate": 9.73675040690808e-07,
+      "loss": 0.001,
+      "reward": 1.3984408378601074,
+      "reward_std": 0.1573176085948944,
+      "rewards/accuracy_reward": 0.302012175321579,
+      "rewards/format_reward": 1.0,
+      "step": 83,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 253.87501525878906,
+      "epoch": 0.005940173962237466,
+      "grad_norm": 2.1552891570371653,
+      "kl": 0.0191650390625,
+      "learning_rate": 9.730426794137726e-07,
+      "loss": 0.0008,
+      "reward": 1.595906376838684,
+      "reward_std": 0.19122400879859924,
+      "rewards/accuracy_reward": 0.5709062814712524,
+      "rewards/format_reward": 1.0,
+      "step": 84,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 224.33929443359375,
+      "epoch": 0.006010890318930769,
+      "grad_norm": 2.468011998898407,
+      "kl": 0.0244140625,
+      "learning_rate": 9.72403023233439e-07,
+      "loss": 0.001,
+      "reward": 1.4167797565460205,
+      "reward_std": 0.04883218929171562,
+      "rewards/accuracy_reward": 0.3489225208759308,
+      "rewards/format_reward": 1.0,
+      "step": 85,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 293.1785888671875,
+      "epoch": 0.006081606675624072,
+      "grad_norm": 3.0951135470999867,
+      "kl": 0.0146484375,
+      "learning_rate": 9.717560820140968e-07,
+      "loss": 0.0006,
+      "reward": 1.6028056144714355,
+      "reward_std": 0.09058967977762222,
+      "rewards/accuracy_reward": 0.4778055250644684,
+      "rewards/format_reward": 1.0,
+      "step": 86,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 242.6607208251953,
+      "epoch": 0.006152323032317375,
+      "grad_norm": 4.0600455292191295,
+      "kl": 0.0169677734375,
+      "learning_rate": 9.711018657323798e-07,
+      "loss": 0.0007,
+      "reward": 1.5601238012313843,
+      "reward_std": 0.14355504512786865,
+      "rewards/accuracy_reward": 0.3851237893104553,
+      "rewards/format_reward": 1.0,
+      "step": 87,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 335.3035888671875,
+      "epoch": 0.006223039389010678,
+      "grad_norm": 6.157136751420816,
+      "kl": 0.00921630859375,
+      "learning_rate": 9.704403844771127e-07,
+      "loss": 0.0004,
+      "reward": 1.4300976991653442,
+      "reward_std": 0.2536827325820923,
+      "rewards/accuracy_reward": 0.3658120036125183,
+      "rewards/format_reward": 1.0,
+      "step": 88,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 249.7678680419922,
+      "epoch": 0.006293755745703981,
+      "grad_norm": 3.1843130127400756,
+      "kl": 0.0250244140625,
+      "learning_rate": 9.697716484491545e-07,
+      "loss": 0.001,
+      "reward": 1.2961429357528687,
+      "reward_std": 0.09949057549238205,
+      "rewards/accuracy_reward": 0.23542852699756622,
+      "rewards/format_reward": 1.0,
+      "step": 89,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 204.85714721679688,
+      "epoch": 0.006364472102397285,
+      "grad_norm": 1.9848526579428263,
+      "kl": 0.0245361328125,
+      "learning_rate": 9.69095667961242e-07,
+      "loss": 0.001,
+      "reward": 1.6368935108184814,
+      "reward_std": 0.0798259824514389,
+      "rewards/accuracy_reward": 0.5618934035301208,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 90,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 321.76788330078125,
+      "epoch": 0.006435188459090587,
+      "grad_norm": 3.0430493637217086,
+      "kl": 0.01806640625,
+      "learning_rate": 9.684124534378306e-07,
+      "loss": 0.0007,
+      "reward": 1.467795968055725,
+      "reward_std": 0.33526092767715454,
+      "rewards/accuracy_reward": 0.43386733531951904,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 91,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 340.6785888671875,
+      "epoch": 0.006505904815783891,
+      "grad_norm": 2.4969561415391914,
+      "kl": 0.0142822265625,
+      "learning_rate": 9.677220154149337e-07,
+      "loss": 0.0006,
+      "reward": 1.4655735492706299,
+      "reward_std": 0.2757211923599243,
+      "rewards/accuracy_reward": 0.3655734360218048,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 92,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 330.51788330078125,
+      "epoch": 0.006576621172477194,
+      "grad_norm": 3.4230740531619244,
+      "kl": 0.0205078125,
+      "learning_rate": 9.670243645399592e-07,
+      "loss": 0.0008,
+      "reward": 1.246590256690979,
+      "reward_std": 0.16154395043849945,
+      "rewards/accuracy_reward": 0.3037329912185669,
+      "rewards/format_reward": 0.8571429252624512,
+      "step": 93,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 266.51788330078125,
+      "epoch": 0.006647337529170497,
+      "grad_norm": 1.792653568726783,
+      "kl": 0.01373291015625,
+      "learning_rate": 9.66319511571547e-07,
+      "loss": 0.0005,
+      "reward": 1.5348743200302124,
+      "reward_std": 0.2590065002441406,
+      "rewards/accuracy_reward": 0.3991599380970001,
+      "rewards/format_reward": 1.0,
+      "step": 94,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 350.8750305175781,
+      "epoch": 0.006718053885863801,
+      "grad_norm": 3.6844148711598894,
+      "kl": 0.0113525390625,
+      "learning_rate": 9.656074673794017e-07,
+      "loss": 0.0005,
+      "reward": 1.3648685216903687,
+      "reward_std": 0.19355671107769012,
+      "rewards/accuracy_reward": 0.29701128602027893,
+      "rewards/format_reward": 0.9285714626312256,
+      "step": 95,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 353.0000305175781,
+      "epoch": 0.006788770242557103,
+      "grad_norm": 1.8425013413449784,
+      "kl": 0.014892578125,
+      "learning_rate": 9.648882429441256e-07,
+      "loss": 0.0006,
+      "reward": 1.3588917255401611,
+      "reward_std": 0.07505875080823898,
+      "rewards/accuracy_reward": 0.28032031655311584,
+      "rewards/format_reward": 1.0,
+      "step": 96,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 241.3035888671875,
+      "epoch": 0.006859486599250407,
+      "grad_norm": 2.2865088411510186,
+      "kl": 0.0186767578125,
+      "learning_rate": 9.641618493570494e-07,
+      "loss": 0.0008,
+      "reward": 1.514050006866455,
+      "reward_std": 0.09278088063001633,
+      "rewards/accuracy_reward": 0.4890500009059906,
+      "rewards/format_reward": 1.0,
+      "step": 97,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 321.64288330078125,
+      "epoch": 0.0069302029559437095,
+      "grad_norm": 2.4393418387911407,
+      "kl": 0.01336669921875,
+      "learning_rate": 9.634282978200603e-07,
+      "loss": 0.0005,
+      "reward": 1.6806771755218506,
+      "reward_std": 0.2365805059671402,
+      "rewards/accuracy_reward": 0.5753200054168701,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 98,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 339.5357360839844,
+      "epoch": 0.007000919312637013,
+      "grad_norm": 1.228627970228306,
+      "kl": 0.0155029296875,
+      "learning_rate": 9.62687599645431e-07,
+      "loss": 0.0006,
+      "reward": 1.3055490255355835,
+      "reward_std": 0.093048594892025,
+      "rewards/accuracy_reward": 0.3126917779445648,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 99,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 359.83929443359375,
+      "epoch": 0.007071635669330316,
+      "grad_norm": 4.909829679120721,
+      "kl": 0.01519775390625,
+      "learning_rate": 9.619397662556433e-07,
+      "loss": 0.0006,
+      "reward": 1.583992838859558,
+      "reward_std": 0.17024964094161987,
+      "rewards/accuracy_reward": 0.4697072505950928,
+      "rewards/format_reward": 1.0,
+      "step": 100,
+      "temporal_rewards": 0.5714285373687744
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c884870e077e73afef500dc4d257c2245d4500ffaef78e17fdae98be2743051e
+size 8440

checkpoint-100/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)