Training in progress, step 100, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/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
+}

last-checkpoint/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 %}"
+}

last-checkpoint/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "Qwen/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
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": 1e-06,
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false
+}

last-checkpoint/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 sha256:8e9fbb56b33c0e46448344479dafcd7dca811bd16e6a526673a8fd6d56fe3998
+size 14215152126

last-checkpoint/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:b5048fcb70c140e619ca0965cfcd4c9ef22616ab360109209fd0711bec611875
+size 14215152126

last-checkpoint/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 sha256:1d8dcadc4f1496f814cdac3f9e5577ff455d31a3c27859841f60b5c7bdb85436
+size 14215152126

last-checkpoint/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:f77c8d0418d62db5b74ccdd829dad517d5d99c9acb2b6a9e04e12dd6bc0eaf65
+size 14215152126

last-checkpoint/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 sha256:458ae437bad08af14a3a6da21f23863ea2d5ac162a09bdb7d0ca5aca1dc3bfb0
+size 14215152126

last-checkpoint/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 sha256:9eef0485fcc6c01fe32bd3cd5c721a0bfe1038f39986ee6cb096fcf34d74cc00
+size 14215152126

last-checkpoint/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 sha256:62aaca59413e85eccdcb83f1c2e826d121da6e7972d92c43c6bc510d19c38010
+size 14215152126

last-checkpoint/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

last-checkpoint/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

last-checkpoint/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

last-checkpoint/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

last-checkpoint/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

last-checkpoint/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

last-checkpoint/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

last-checkpoint/latest

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

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17617993c9ab5ac2116987aaf38c656381aad905c9352a51490240d419ff62c0
+size 4968243304

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74de14f01bda96ffd2500e51d2adf6c03dcfddbbdf2f43d9e6fd5cd0a468cf32
+size 4991495816

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccc8801f5f67aca7730d65a3c89c8f32dcd5ce336648141fd90121b49dfa341
+size 4932751040

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ea50eb6fd468e2b667401050cbd946dc934f921aba63412c39db07f0c17365
+size 1691924384

last-checkpoint/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"
+  }
+}

last-checkpoint/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
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:763d5c131591370f1d52b0aa6539f70eb8a0c4954a5e78506f6bc04c58290268
+size 15920

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41e4943e97c73bf1f3efd422e4751fcc4d0280de08a84f1d7632c069262b2ea2
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263f74fcd6ec7d3f1e5860961b69bd7aff70b57a1501e93d7925d34fb10771c2
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08fc622393e6882dbb12ed2672791bf0ded63c3839d552c9757b2b0666df2605
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb60e8fee28ece71f42072f2bb5e97094fd154ff3765f3cfc657681677009c9b
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7952a23b43e2483b709361dc6b1ab6ea926ab56c77ee8647a336b76cfd19453
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4bd7ddb0e4a9ffc86f475a180bc7c78d74e0443fc583113c88e42041fc1de1
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb5f68596479240ce42efa6cf5449fb202686261075cf439a50da4f70f32fda5
+size 1064

last-checkpoint/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
+  }
+}

last-checkpoint/tokenizer.json

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

last-checkpoint/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": "{% 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 %}",
+  "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
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,1633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.003852228514195462,
+  "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": 0.2857142857142857,
+      "completion_length": 194.5178680419922,
+      "epoch": 3.852228514195462e-05,
+      "grad_norm": 4.569568275684066,
+      "kl": 0.0,
+      "learning_rate": 9.999999963384595e-07,
+      "loss": -0.0,
+      "reward": 0.9388507008552551,
+      "reward_std": 0.5055427551269531,
+      "rewards/accuracy_reward": 0.36027929186820984,
+      "rewards/format_reward": 0.5,
+      "step": 1,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 201.85714721679688,
+      "epoch": 7.704457028390924e-05,
+      "grad_norm": 7.3425194668816305,
+      "kl": 0.001190185546875,
+      "learning_rate": 9.99999985353838e-07,
+      "loss": 0.0,
+      "reward": 1.155859351158142,
+      "reward_std": 0.6079983711242676,
+      "rewards/accuracy_reward": 0.5290736556053162,
+      "rewards/format_reward": 0.5714285969734192,
+      "step": 2,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 229.5357208251953,
+      "epoch": 0.00011556685542586386,
+      "grad_norm": 10.46166634557011,
+      "kl": 0.00148773193359375,
+      "learning_rate": 9.999999670461361e-07,
+      "loss": 0.0001,
+      "reward": 1.0399483442306519,
+      "reward_std": 0.527042806148529,
+      "rewards/accuracy_reward": 0.3810196816921234,
+      "rewards/format_reward": 0.5535714626312256,
+      "step": 3,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 243.50001525878906,
+      "epoch": 0.00015408914056781847,
+      "grad_norm": 2.4261998522622483,
+      "kl": 0.0020599365234375,
+      "learning_rate": 9.999999414153537e-07,
+      "loss": 0.0001,
+      "reward": 0.8851699829101562,
+      "reward_std": 0.5343522429466248,
+      "rewards/accuracy_reward": 0.27624136209487915,
+      "rewards/format_reward": 0.5892857313156128,
+      "step": 4,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 298.8214416503906,
+      "epoch": 0.0001926114257097731,
+      "grad_norm": 2.6156215584160614,
+      "kl": 0.005035400390625,
+      "learning_rate": 9.999999084614913e-07,
+      "loss": 0.0002,
+      "reward": 1.374528408050537,
+      "reward_std": 0.558069109916687,
+      "rewards/accuracy_reward": 0.5459570288658142,
+      "rewards/format_reward": 0.6785714626312256,
+      "step": 5,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 246.3035888671875,
+      "epoch": 0.00023113371085172773,
+      "grad_norm": 3.003642956951274,
+      "kl": 0.003936767578125,
+      "learning_rate": 9.999998681845493e-07,
+      "loss": 0.0002,
+      "reward": 1.5285981893539429,
+      "reward_std": 0.3147147297859192,
+      "rewards/accuracy_reward": 0.5000267028808594,
+      "rewards/format_reward": 0.8750000596046448,
+      "step": 6,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 172.80357360839844,
+      "epoch": 0.0002696559959936823,
+      "grad_norm": 2.2475007240283,
+      "kl": 0.00531005859375,
+      "learning_rate": 9.999998205845283e-07,
+      "loss": 0.0002,
+      "reward": 1.4922091960906982,
+      "reward_std": 0.26347360014915466,
+      "rewards/accuracy_reward": 0.46542346477508545,
+      "rewards/format_reward": 0.9285714626312256,
+      "step": 7,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 264.125,
+      "epoch": 0.00030817828113563695,
+      "grad_norm": 13.215726344682453,
+      "kl": 0.004608154296875,
+      "learning_rate": 9.99999765661429e-07,
+      "loss": 0.0002,
+      "reward": 1.4859822988510132,
+      "reward_std": 0.39378076791763306,
+      "rewards/accuracy_reward": 0.38955357670783997,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 8,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 233.75001525878906,
+      "epoch": 0.0003467005662775916,
+      "grad_norm": 1.8754887680204013,
+      "kl": 0.0047607421875,
+      "learning_rate": 9.999997034152522e-07,
+      "loss": 0.0002,
+      "reward": 1.5294489860534668,
+      "reward_std": 0.35142022371292114,
+      "rewards/accuracy_reward": 0.5062346458435059,
+      "rewards/format_reward": 0.9285714626312256,
+      "step": 9,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 184.6428680419922,
+      "epoch": 0.0003852228514195462,
+      "grad_norm": 6.068013472130498,
+      "kl": 0.0108642578125,
+      "learning_rate": 9.99999633845999e-07,
+      "loss": 0.0004,
+      "reward": 1.1100354194641113,
+      "reward_std": 0.11215802282094955,
+      "rewards/accuracy_reward": 0.11717834323644638,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 10,
+      "temporal_rewards": 0.357142835855484
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 130.80357360839844,
+      "epoch": 0.0004237451365615008,
+      "grad_norm": 2.7706073106467994,
+      "kl": 0.00799560546875,
+      "learning_rate": 9.9999955695367e-07,
+      "loss": 0.0003,
+      "reward": 1.6379828453063965,
+      "reward_std": 0.15209504961967468,
+      "rewards/accuracy_reward": 0.5522685050964355,
+      "rewards/format_reward": 1.0,
+      "step": 11,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 231.0535888671875,
+      "epoch": 0.00046226742170345545,
+      "grad_norm": 4.077451010264333,
+      "kl": 0.0135498046875,
+      "learning_rate": 9.999994727382667e-07,
+      "loss": 0.0005,
+      "reward": 1.757586121559143,
+      "reward_std": 0.1790602058172226,
+      "rewards/accuracy_reward": 0.6308003664016724,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 12,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 182.85714721679688,
+      "epoch": 0.0005007897068454101,
+      "grad_norm": 3.171637082851311,
+      "kl": 0.01470947265625,
+      "learning_rate": 9.999993811997902e-07,
+      "loss": 0.0006,
+      "reward": 1.5119588375091553,
+      "reward_std": 0.0800565853714943,
+      "rewards/accuracy_reward": 0.374458909034729,
+      "rewards/format_reward": 1.0,
+      "step": 13,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 369.9821472167969,
+      "epoch": 0.0005393119919873646,
+      "grad_norm": 3.0114431906272743,
+      "kl": 0.009033203125,
+      "learning_rate": 9.99999282338242e-07,
+      "loss": 0.0004,
+      "reward": 1.1452234983444214,
+      "reward_std": 0.30584630370140076,
+      "rewards/accuracy_reward": 0.2773663103580475,
+      "rewards/format_reward": 0.8392857313156128,
+      "step": 14,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 272.3214416503906,
+      "epoch": 0.0005778342771293193,
+      "grad_norm": 1.762681908155442,
+      "kl": 0.0123291015625,
+      "learning_rate": 9.999991761536231e-07,
+      "loss": 0.0005,
+      "reward": 1.3017858266830444,
+      "reward_std": 0.21957917511463165,
+      "rewards/accuracy_reward": 0.2857142984867096,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 15,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 167.7857208251953,
+      "epoch": 0.0006163565622712739,
+      "grad_norm": 2.3136273405544956,
+      "kl": 0.01318359375,
+      "learning_rate": 9.999990626459356e-07,
+      "loss": 0.0005,
+      "reward": 1.4714285135269165,
+      "reward_std": 0.27723559737205505,
+      "rewards/accuracy_reward": 0.42500004172325134,
+      "rewards/format_reward": 1.0,
+      "step": 16,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 145.1428680419922,
+      "epoch": 0.0006548788474132286,
+      "grad_norm": 2.6755799727485496,
+      "kl": 0.0140380859375,
+      "learning_rate": 9.99998941815181e-07,
+      "loss": 0.0006,
+      "reward": 1.779188632965088,
+      "reward_std": 0.21795018017292023,
+      "rewards/accuracy_reward": 0.7077600359916687,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 17,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 220.1607208251953,
+      "epoch": 0.0006934011325551831,
+      "grad_norm": 2.051492241832231,
+      "kl": 0.0130615234375,
+      "learning_rate": 9.999988136613608e-07,
+      "loss": 0.0005,
+      "reward": 1.5756233930587769,
+      "reward_std": 0.2738674283027649,
+      "rewards/accuracy_reward": 0.4952661097049713,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 18,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 159.71429443359375,
+      "epoch": 0.0007319234176971378,
+      "grad_norm": 7.813403350492354,
+      "kl": 0.0228271484375,
+      "learning_rate": 9.999986781844772e-07,
+      "loss": 0.0009,
+      "reward": 1.368477463722229,
+      "reward_std": 0.17073635756969452,
+      "rewards/accuracy_reward": 0.320263147354126,
+      "rewards/format_reward": 1.0,
+      "step": 19,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 245.96429443359375,
+      "epoch": 0.0007704457028390924,
+      "grad_norm": 3.1470469127291536,
+      "kl": 0.01239013671875,
+      "learning_rate": 9.99998535384532e-07,
+      "loss": 0.0005,
+      "reward": 1.4473823308944702,
+      "reward_std": 0.17675410211086273,
+      "rewards/accuracy_reward": 0.34738224744796753,
+      "rewards/format_reward": 1.0,
+      "step": 20,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 196.67857360839844,
+      "epoch": 0.0008089679879810471,
+      "grad_norm": 1.985055486033898,
+      "kl": 0.0172119140625,
+      "learning_rate": 9.999983852615273e-07,
+      "loss": 0.0007,
+      "reward": 1.5379002094268799,
+      "reward_std": 0.10025887936353683,
+      "rewards/accuracy_reward": 0.4736144542694092,
+      "rewards/format_reward": 1.0,
+      "step": 21,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 235.75001525878906,
+      "epoch": 0.0008474902731230017,
+      "grad_norm": 2.3022387425335356,
+      "kl": 0.010009765625,
+      "learning_rate": 9.999982278154653e-07,
+      "loss": 0.0004,
+      "reward": 1.3792414665222168,
+      "reward_std": 0.16881819069385529,
+      "rewards/accuracy_reward": 0.3149556815624237,
+      "rewards/format_reward": 1.0,
+      "step": 22,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 195.75001525878906,
+      "epoch": 0.0008860125582649563,
+      "grad_norm": 2.5960019564354115,
+      "kl": 0.01373291015625,
+      "learning_rate": 9.999980630463484e-07,
+      "loss": 0.0006,
+      "reward": 1.483102560043335,
+      "reward_std": 0.2669390141963959,
+      "rewards/accuracy_reward": 0.43310248851776123,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 23,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 233.58929443359375,
+      "epoch": 0.0009245348434069109,
+      "grad_norm": 16.12922501556988,
+      "kl": 0.0169677734375,
+      "learning_rate": 9.99997890954179e-07,
+      "loss": 0.0007,
+      "reward": 1.253800868988037,
+      "reward_std": 0.2512234151363373,
+      "rewards/accuracy_reward": 0.4055865705013275,
+      "rewards/format_reward": 0.8392857313156128,
+      "step": 24,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 198.7857208251953,
+      "epoch": 0.0009630571285488655,
+      "grad_norm": 3.9868394906657,
+      "kl": 0.0263671875,
+      "learning_rate": 9.999977115389595e-07,
+      "loss": 0.0011,
+      "reward": 1.821338176727295,
+      "reward_std": 0.2050185352563858,
+      "rewards/accuracy_reward": 0.6606237888336182,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 25,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 194.73214721679688,
+      "epoch": 0.0010015794136908202,
+      "grad_norm": 3.0965250094321854,
+      "kl": 0.015869140625,
+      "learning_rate": 9.999975248006927e-07,
+      "loss": 0.0006,
+      "reward": 1.5368238687515259,
+      "reward_std": 0.29229164123535156,
+      "rewards/accuracy_reward": 0.49039536714553833,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 26,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 144.58929443359375,
+      "epoch": 0.0010401016988327747,
+      "grad_norm": 3.463559757421393,
+      "kl": 0.0194091796875,
+      "learning_rate": 9.999973307393812e-07,
+      "loss": 0.0008,
+      "reward": 1.9461054801940918,
+      "reward_std": 0.14775770902633667,
+      "rewards/accuracy_reward": 0.7211053371429443,
+      "rewards/format_reward": 1.0,
+      "step": 27,
+      "temporal_rewards": 0.8571428656578064
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 149.5178680419922,
+      "epoch": 0.0010786239839747293,
+      "grad_norm": 4.208967606472135,
+      "kl": 0.0166015625,
+      "learning_rate": 9.99997129355028e-07,
+      "loss": 0.0007,
+      "reward": 1.4785715341567993,
+      "reward_std": 0.23233509063720703,
+      "rewards/accuracy_reward": 0.4107142984867096,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 28,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 190.07144165039062,
+      "epoch": 0.001117146269116684,
+      "grad_norm": 3.1320237643372493,
+      "kl": 0.019287109375,
+      "learning_rate": 9.999969206476357e-07,
+      "loss": 0.0008,
+      "reward": 1.6795918941497803,
+      "reward_std": 0.2941642701625824,
+      "rewards/accuracy_reward": 0.59566330909729,
+      "rewards/format_reward": 1.0,
+      "step": 29,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 140.67857360839844,
+      "epoch": 0.0011556685542586387,
+      "grad_norm": 2.1228282157999563,
+      "kl": 0.0218505859375,
+      "learning_rate": 9.999967046172078e-07,
+      "loss": 0.0009,
+      "reward": 1.5656999349594116,
+      "reward_std": 0.23240727186203003,
+      "rewards/accuracy_reward": 0.4746284782886505,
+      "rewards/format_reward": 1.0,
+      "step": 30,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 342.0535888671875,
+      "epoch": 0.0011941908394005932,
+      "grad_norm": 3.139985295701204,
+      "kl": 0.01708984375,
+      "learning_rate": 9.999964812637472e-07,
+      "loss": 0.0007,
+      "reward": 1.1670215129852295,
+      "reward_std": 0.2952883243560791,
+      "rewards/accuracy_reward": 0.25273576378822327,
+      "rewards/format_reward": 0.8750000596046448,
+      "step": 31,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.5714285714285714,
+      "completion_length": 320.375,
+      "epoch": 0.0012327131245425478,
+      "grad_norm": 2.9321327508284014,
+      "kl": 0.015869140625,
+      "learning_rate": 9.999962505872572e-07,
+      "loss": 0.0006,
+      "reward": 1.0767621994018555,
+      "reward_std": 0.18118657171726227,
+      "rewards/accuracy_reward": 0.18033367395401,
+      "rewards/format_reward": 0.8571429252624512,
+      "step": 32,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 182.80357360839844,
+      "epoch": 0.0012712354096845026,
+      "grad_norm": 1.6393422027112028,
+      "kl": 0.029296875,
+      "learning_rate": 9.999960125877412e-07,
+      "loss": 0.0012,
+      "reward": 1.662595272064209,
+      "reward_std": 0.0667729526758194,
+      "rewards/accuracy_reward": 0.5947380065917969,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 33,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 280.1964416503906,
+      "epoch": 0.0013097576948264572,
+      "grad_norm": 1.8796443825485132,
+      "kl": 0.0194091796875,
+      "learning_rate": 9.999957672652028e-07,
+      "loss": 0.0008,
+      "reward": 1.3545540571212769,
+      "reward_std": 0.18943731486797333,
+      "rewards/accuracy_reward": 0.3545539975166321,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 34,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.0,
+      "completion_length": 219.37501525878906,
+      "epoch": 0.0013482799799684117,
+      "grad_norm": 2.906310484540033,
+      "kl": 0.015380859375,
+      "learning_rate": 9.999955146196455e-07,
+      "loss": 0.0006,
+      "reward": 1.3780333995819092,
+      "reward_std": 0.23713341355323792,
+      "rewards/accuracy_reward": 0.3244618773460388,
+      "rewards/format_reward": 1.0,
+      "step": 35,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 279.51788330078125,
+      "epoch": 0.0013868022651103663,
+      "grad_norm": 2.4420138636907334,
+      "kl": 0.01116943359375,
+      "learning_rate": 9.999952546510728e-07,
+      "loss": 0.0004,
+      "reward": 1.4657601118087769,
+      "reward_std": 0.24927140772342682,
+      "rewards/accuracy_reward": 0.3657601475715637,
+      "rewards/format_reward": 1.0,
+      "step": 36,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 188.92857360839844,
+      "epoch": 0.0014253245502523209,
+      "grad_norm": 6.501680028535296,
+      "kl": 0.0191650390625,
+      "learning_rate": 9.99994987359489e-07,
+      "loss": 0.0008,
+      "reward": 1.6103023290634155,
+      "reward_std": 0.34319451451301575,
+      "rewards/accuracy_reward": 0.519230842590332,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 37,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 174.1607208251953,
+      "epoch": 0.0014638468353942757,
+      "grad_norm": 2.6403997571984985,
+      "kl": 0.02001953125,
+      "learning_rate": 9.999947127448973e-07,
+      "loss": 0.0008,
+      "reward": 1.617859959602356,
+      "reward_std": 0.2102932333946228,
+      "rewards/accuracy_reward": 0.5214312076568604,
+      "rewards/format_reward": 1.0,
+      "step": 38,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 157.8928680419922,
+      "epoch": 0.0015023691205362302,
+      "grad_norm": 2.1234203792687825,
+      "kl": 0.015380859375,
+      "learning_rate": 9.999944308073023e-07,
+      "loss": 0.0006,
+      "reward": 1.7400298118591309,
+      "reward_std": 0.20839495956897736,
+      "rewards/accuracy_reward": 0.6168155074119568,
+      "rewards/format_reward": 1.0,
+      "step": 39,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 243.60714721679688,
+      "epoch": 0.0015408914056781848,
+      "grad_norm": 5.213110939689996,
+      "kl": 0.0146484375,
+      "learning_rate": 9.999941415467079e-07,
+      "loss": 0.0006,
+      "reward": 1.2147839069366455,
+      "reward_std": 0.29392552375793457,
+      "rewards/accuracy_reward": 0.17014095187187195,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 40,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 218.5357208251953,
+      "epoch": 0.0015794136908201394,
+      "grad_norm": 2.1683694673772105,
+      "kl": 0.0164794921875,
+      "learning_rate": 9.999938449631185e-07,
+      "loss": 0.0007,
+      "reward": 1.5682185888290405,
+      "reward_std": 0.3265009820461273,
+      "rewards/accuracy_reward": 0.45928990840911865,
+      "rewards/format_reward": 1.0,
+      "step": 41,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 136.08929443359375,
+      "epoch": 0.0016179359759620942,
+      "grad_norm": 2.6763843398967846,
+      "kl": 0.0224609375,
+      "learning_rate": 9.999935410565385e-07,
+      "loss": 0.0009,
+      "reward": 1.412774920463562,
+      "reward_std": 0.15946559607982635,
+      "rewards/accuracy_reward": 0.3217034339904785,
+      "rewards/format_reward": 1.0,
+      "step": 42,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 134.46429443359375,
+      "epoch": 0.0016564582611040487,
+      "grad_norm": 2.7136415500998874,
+      "kl": 0.01953125,
+      "learning_rate": 9.999932298269719e-07,
+      "loss": 0.0008,
+      "reward": 1.8830357789993286,
+      "reward_std": 0.30814799666404724,
+      "rewards/accuracy_reward": 0.7330358028411865,
+      "rewards/format_reward": 1.0,
+      "step": 43,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 224.19644165039062,
+      "epoch": 0.0016949805462460033,
+      "grad_norm": 10.61289783068452,
+      "kl": 0.017333984375,
+      "learning_rate": 9.999929112744236e-07,
+      "loss": 0.0007,
+      "reward": 1.6218483448028564,
+      "reward_std": 0.13741520047187805,
+      "rewards/accuracy_reward": 0.5432767868041992,
+      "rewards/format_reward": 0.9642857313156128,
+      "step": 44,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 175.7678680419922,
+      "epoch": 0.0017335028313879579,
+      "grad_norm": 3.0540147056191245,
+      "kl": 0.0233154296875,
+      "learning_rate": 9.999925853988984e-07,
+      "loss": 0.0009,
+      "reward": 1.7440528869628906,
+      "reward_std": 0.23217743635177612,
+      "rewards/accuracy_reward": 0.6190527677536011,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 45,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.7142857142857143,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 176.33929443359375,
+      "epoch": 0.0017720251165299127,
+      "grad_norm": 0.6517269698965342,
+      "kl": 0.019287109375,
+      "learning_rate": 9.999922522004008e-07,
+      "loss": 0.0008,
+      "reward": 1.946428656578064,
+      "reward_std": 0.05050762742757797,
+      "rewards/accuracy_reward": 0.7321428656578064,
+      "rewards/format_reward": 1.0,
+      "step": 46,
+      "temporal_rewards": 0.8571428656578064
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 295.4464416503906,
+      "epoch": 0.0018105474016718672,
+      "grad_norm": 1.9801638924884892,
+      "kl": 0.0146484375,
+      "learning_rate": 9.999919116789358e-07,
+      "loss": 0.0006,
+      "reward": 1.6217808723449707,
+      "reward_std": 0.19541169703006744,
+      "rewards/accuracy_reward": 0.5967808961868286,
+      "rewards/format_reward": 0.9285714626312256,
+      "step": 47,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 236.21429443359375,
+      "epoch": 0.0018490696868138218,
+      "grad_norm": 1.1223975598836913,
+      "kl": 0.01904296875,
+      "learning_rate": 9.999915638345082e-07,
+      "loss": 0.0008,
+      "reward": 1.653198003768921,
+      "reward_std": 0.17088621854782104,
+      "rewards/accuracy_reward": 0.6174837350845337,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 48,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 254.2857208251953,
+      "epoch": 0.0018875919719557764,
+      "grad_norm": 3.796030516352467,
+      "kl": 0.01556396484375,
+      "learning_rate": 9.999912086671234e-07,
+      "loss": 0.0006,
+      "reward": 1.6027967929840088,
+      "reward_std": 0.33174049854278564,
+      "rewards/accuracy_reward": 0.4742252230644226,
+      "rewards/format_reward": 1.0,
+      "step": 49,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 138.58929443359375,
+      "epoch": 0.001926114257097731,
+      "grad_norm": 11.63273957332234,
+      "kl": 0.02490234375,
+      "learning_rate": 9.999908461767864e-07,
+      "loss": 0.001,
+      "reward": 1.532570242881775,
+      "reward_std": 0.324184775352478,
+      "rewards/accuracy_reward": 0.4379273056983948,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 50,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 303.8214416503906,
+      "epoch": 0.0019646365422396855,
+      "grad_norm": 1.472520440759773,
+      "kl": 0.01611328125,
+      "learning_rate": 9.999904763635026e-07,
+      "loss": 0.0006,
+      "reward": 1.329949975013733,
+      "reward_std": 0.2325875461101532,
+      "rewards/accuracy_reward": 0.22994986176490784,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 51,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 233.10714721679688,
+      "epoch": 0.0020031588273816403,
+      "grad_norm": 6.083305961655314,
+      "kl": 0.01806640625,
+      "learning_rate": 9.999900992272773e-07,
+      "loss": 0.0007,
+      "reward": 1.2669223546981812,
+      "reward_std": 0.1918085664510727,
+      "rewards/accuracy_reward": 0.19906513392925262,
+      "rewards/format_reward": 1.0,
+      "step": 52,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 114.10714721679688,
+      "epoch": 0.002041681112523595,
+      "grad_norm": 2.7012427152402654,
+      "kl": 0.032958984375,
+      "learning_rate": 9.999897147681163e-07,
+      "loss": 0.0013,
+      "reward": 1.7964287996292114,
+      "reward_std": 0.2886441946029663,
+      "rewards/accuracy_reward": 0.7321428656578064,
+      "rewards/format_reward": 1.0,
+      "step": 53,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 185.7678680419922,
+      "epoch": 0.0020802033976655494,
+      "grad_norm": 3.499372150686523,
+      "kl": 0.0224609375,
+      "learning_rate": 9.999893229860249e-07,
+      "loss": 0.0009,
+      "reward": 1.4564489126205444,
+      "reward_std": 0.25798067450523376,
+      "rewards/accuracy_reward": 0.381448894739151,
+      "rewards/format_reward": 1.0,
+      "step": 54,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 201.33929443359375,
+      "epoch": 0.0021187256828075042,
+      "grad_norm": 1.8808446859449741,
+      "kl": 0.021728515625,
+      "learning_rate": 9.999889238810088e-07,
+      "loss": 0.0009,
+      "reward": 1.5330215692520142,
+      "reward_std": 0.21871158480644226,
+      "rewards/accuracy_reward": 0.45266443490982056,
+      "rewards/format_reward": 1.0,
+      "step": 55,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 193.0178680419922,
+      "epoch": 0.0021572479679494586,
+      "grad_norm": 3.822445715369176,
+      "kl": 0.0242919921875,
+      "learning_rate": 9.999885174530742e-07,
+      "loss": 0.001,
+      "reward": 1.293078899383545,
+      "reward_std": 0.10130374878644943,
+      "rewards/accuracy_reward": 0.278793066740036,
+      "rewards/format_reward": 1.0,
+      "step": 56,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 246.50001525878906,
+      "epoch": 0.0021957702530914134,
+      "grad_norm": 2.6785361100208043,
+      "kl": 0.0218505859375,
+      "learning_rate": 9.999881037022268e-07,
+      "loss": 0.0009,
+      "reward": 1.6220659017562866,
+      "reward_std": 0.306893914937973,
+      "rewards/accuracy_reward": 0.47028017044067383,
+      "rewards/format_reward": 1.0,
+      "step": 57,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 206.55357360839844,
+      "epoch": 0.002234292538233368,
+      "grad_norm": 2.231409411826765,
+      "kl": 0.027099609375,
+      "learning_rate": 9.999876826284728e-07,
+      "loss": 0.0011,
+      "reward": 1.5493416786193848,
+      "reward_std": 0.15240609645843506,
+      "rewards/accuracy_reward": 0.47434163093566895,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 58,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 216.94644165039062,
+      "epoch": 0.0022728148233753225,
+      "grad_norm": 2.6320081221943967,
+      "kl": 0.0181884765625,
+      "learning_rate": 9.999872542318182e-07,
+      "loss": 0.0007,
+      "reward": 1.264460802078247,
+      "reward_std": 0.1528075784444809,
+      "rewards/accuracy_reward": 0.2269606739282608,
+      "rewards/format_reward": 1.0,
+      "step": 59,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 153.85714721679688,
+      "epoch": 0.0023113371085172773,
+      "grad_norm": 2.3218624177616936,
+      "kl": 0.0262451171875,
+      "learning_rate": 9.999868185122694e-07,
+      "loss": 0.0011,
+      "reward": 1.5643600225448608,
+      "reward_std": 0.17870767414569855,
+      "rewards/accuracy_reward": 0.5179314017295837,
+      "rewards/format_reward": 1.0,
+      "step": 60,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 194.94644165039062,
+      "epoch": 0.0023498593936592317,
+      "grad_norm": 2.4059506047191412,
+      "kl": 0.02783203125,
+      "learning_rate": 9.999863754698328e-07,
+      "loss": 0.0011,
+      "reward": 1.7017457485198975,
+      "reward_std": 0.21297064423561096,
+      "rewards/accuracy_reward": 0.596388578414917,
+      "rewards/format_reward": 1.0,
+      "step": 61,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 263.1964416503906,
+      "epoch": 0.0023883816788011865,
+      "grad_norm": 7.79968970295138,
+      "kl": 0.025146484375,
+      "learning_rate": 9.999859251045148e-07,
+      "loss": 0.001,
+      "reward": 1.3235949277877808,
+      "reward_std": 0.3387552797794342,
+      "rewards/accuracy_reward": 0.32002341747283936,
+      "rewards/format_reward": 0.9285714626312256,
+      "step": 62,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 282.875,
+      "epoch": 0.0024269039639431412,
+      "grad_norm": 11.820097516090824,
+      "kl": 0.0230712890625,
+      "learning_rate": 9.999854674163223e-07,
+      "loss": 0.0009,
+      "reward": 1.4603477716445923,
+      "reward_std": 0.1610259860754013,
+      "rewards/accuracy_reward": 0.3817763030529022,
+      "rewards/format_reward": 1.0,
+      "step": 63,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.42857142857142855,
+      "completion_length": 145.7857208251953,
+      "epoch": 0.0024654262490850956,
+      "grad_norm": 2.198227643716255,
+      "kl": 0.03076171875,
+      "learning_rate": 9.999850024052612e-07,
+      "loss": 0.0012,
+      "reward": 1.623809576034546,
+      "reward_std": 0.15851996839046478,
+      "rewards/accuracy_reward": 0.523809552192688,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 64,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 227.98214721679688,
+      "epoch": 0.0025039485342270504,
+      "grad_norm": 2.0716605728346225,
+      "kl": 0.021728515625,
+      "learning_rate": 9.999845300713392e-07,
+      "loss": 0.0009,
+      "reward": 1.4685227870941162,
+      "reward_std": 0.23074626922607422,
+      "rewards/accuracy_reward": 0.4185227155685425,
+      "rewards/format_reward": 1.0,
+      "step": 65,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 223.07144165039062,
+      "epoch": 0.002542470819369005,
+      "grad_norm": 12.068459853286635,
+      "kl": 0.0284423828125,
+      "learning_rate": 9.999840504145628e-07,
+      "loss": 0.0011,
+      "reward": 1.6151973009109497,
+      "reward_std": 0.184441938996315,
+      "rewards/accuracy_reward": 0.516982913017273,
+      "rewards/format_reward": 1.0,
+      "step": 66,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.5714285714285714,
+      "all_wrong": 0.0,
+      "completion_length": 179.3928680419922,
+      "epoch": 0.0025809931045109595,
+      "grad_norm": 1.9797102708238594,
+      "kl": 0.022705078125,
+      "learning_rate": 9.99983563434939e-07,
+      "loss": 0.0009,
+      "reward": 1.8434789180755615,
+      "reward_std": 0.09488734602928162,
+      "rewards/accuracy_reward": 0.657764732837677,
+      "rewards/format_reward": 1.0,
+      "step": 67,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 260.4464416503906,
+      "epoch": 0.0026195153896529143,
+      "grad_norm": 1.3994503258018347,
+      "kl": 0.018798828125,
+      "learning_rate": 9.999830691324754e-07,
+      "loss": 0.0008,
+      "reward": 1.5176632404327393,
+      "reward_std": 0.16758570075035095,
+      "rewards/accuracy_reward": 0.4533773958683014,
+      "rewards/format_reward": 1.0,
+      "step": 68,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 154.3928680419922,
+      "epoch": 0.0026580376747948687,
+      "grad_norm": 2.478716497709362,
+      "kl": 0.024169921875,
+      "learning_rate": 9.999825675071785e-07,
+      "loss": 0.001,
+      "reward": 1.7284132242202759,
+      "reward_std": 0.1862778216600418,
+      "rewards/accuracy_reward": 0.5909132361412048,
+      "rewards/format_reward": 1.0,
+      "step": 69,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 218.08929443359375,
+      "epoch": 0.0026965599599368235,
+      "grad_norm": 3.2636585667285747,
+      "kl": 0.018798828125,
+      "learning_rate": 9.999820585590562e-07,
+      "loss": 0.0008,
+      "reward": 1.8550920486450195,
+      "reward_std": 0.18145045638084412,
+      "rewards/accuracy_reward": 0.6693777441978455,
+      "rewards/format_reward": 1.0,
+      "step": 70,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.2857142857142857,
+      "completion_length": 166.0178680419922,
+      "epoch": 0.0027350822450787782,
+      "grad_norm": 2.44595510707876,
+      "kl": 0.0220947265625,
+      "learning_rate": 9.999815422881156e-07,
+      "loss": 0.0009,
+      "reward": 1.6340795755386353,
+      "reward_std": 0.14490874111652374,
+      "rewards/accuracy_reward": 0.49479392170906067,
+      "rewards/format_reward": 1.0,
+      "step": 71,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 228.44644165039062,
+      "epoch": 0.0027736045302207326,
+      "grad_norm": 4.715787174655585,
+      "kl": 0.0189208984375,
+      "learning_rate": 9.999810186943645e-07,
+      "loss": 0.0008,
+      "reward": 1.8304548263549805,
+      "reward_std": 0.26317012310028076,
+      "rewards/accuracy_reward": 0.6572403311729431,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 72,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.5714285714285714,
+      "all_wrong": 0.0,
+      "completion_length": 281.5,
+      "epoch": 0.0028121268153626874,
+      "grad_norm": 4.5915608298302955,
+      "kl": 0.0186767578125,
+      "learning_rate": 9.999804877778105e-07,
+      "loss": 0.0007,
+      "reward": 1.8425076007843018,
+      "reward_std": 0.19430917501449585,
+      "rewards/accuracy_reward": 0.6567932367324829,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 73,
+      "temporal_rewards": 0.8571428656578064
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 187.0357208251953,
+      "epoch": 0.0028506491005046417,
+      "grad_norm": 2.861793907089711,
+      "kl": 0.01953125,
+      "learning_rate": 9.999799495384613e-07,
+      "loss": 0.0008,
+      "reward": 1.5369635820388794,
+      "reward_std": 0.19547729194164276,
+      "rewards/accuracy_reward": 0.47446346282958984,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 74,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 204.00001525878906,
+      "epoch": 0.0028891713856465965,
+      "grad_norm": 3.6528625470246756,
+      "kl": 0.018798828125,
+      "learning_rate": 9.99979403976325e-07,
+      "loss": 0.0008,
+      "reward": 1.3830876350402832,
+      "reward_std": 0.1895177811384201,
+      "rewards/accuracy_reward": 0.3688018023967743,
+      "rewards/format_reward": 1.0,
+      "step": 75,
+      "temporal_rewards": 0.5
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 158.30357360839844,
+      "epoch": 0.0029276936707885513,
+      "grad_norm": 5.083277470007981,
+      "kl": 0.0220947265625,
+      "learning_rate": 9.999788510914095e-07,
+      "loss": 0.0009,
+      "reward": 1.834609031677246,
+      "reward_std": 0.19010314345359802,
+      "rewards/accuracy_reward": 0.7542517185211182,
+      "rewards/format_reward": 1.0,
+      "step": 76,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 283.46429443359375,
+      "epoch": 0.0029662159559305057,
+      "grad_norm": 2.6220465157846515,
+      "kl": 0.0159912109375,
+      "learning_rate": 9.999782908837226e-07,
+      "loss": 0.0006,
+      "reward": 1.2294546365737915,
+      "reward_std": 0.20362988114356995,
+      "rewards/accuracy_reward": 0.2901688516139984,
+      "rewards/format_reward": 0.910714328289032,
+      "step": 77,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 269.4464416503906,
+      "epoch": 0.0030047382410724605,
+      "grad_norm": 3.6931368985139565,
+      "kl": 0.01953125,
+      "learning_rate": 9.999777233532728e-07,
+      "loss": 0.0008,
+      "reward": 1.3699510097503662,
+      "reward_std": 0.2626003324985504,
+      "rewards/accuracy_reward": 0.2985224425792694,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 78,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 253.58929443359375,
+      "epoch": 0.0030432605262144152,
+      "grad_norm": 2.4812016013725247,
+      "kl": 0.0166015625,
+      "learning_rate": 9.999771485000686e-07,
+      "loss": 0.0007,
+      "reward": 1.6232998371124268,
+      "reward_std": 0.3576071560382843,
+      "rewards/accuracy_reward": 0.4857998788356781,
+      "rewards/format_reward": 1.0,
+      "step": 79,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 233.0178680419922,
+      "epoch": 0.0030817828113563696,
+      "grad_norm": 2.5348454122960544,
+      "kl": 0.0162353515625,
+      "learning_rate": 9.99976566324118e-07,
+      "loss": 0.0007,
+      "reward": 1.5126162767410278,
+      "reward_std": 0.3677576184272766,
+      "rewards/accuracy_reward": 0.5126160979270935,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 80,
+      "temporal_rewards": 0.357142835855484
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 340.2857360839844,
+      "epoch": 0.0031203050964983244,
+      "grad_norm": 2.1615647344294318,
+      "kl": 0.01361083984375,
+      "learning_rate": 9.999759768254296e-07,
+      "loss": 0.0005,
+      "reward": 1.640975832939148,
+      "reward_std": 0.23601117730140686,
+      "rewards/accuracy_reward": 0.5302614569664001,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 81,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 141.125,
+      "epoch": 0.0031588273816402787,
+      "grad_norm": 2.7836789740348973,
+      "kl": 0.0240478515625,
+      "learning_rate": 9.999753800040124e-07,
+      "loss": 0.001,
+      "reward": 1.6339308023452759,
+      "reward_std": 0.19026820361614227,
+      "rewards/accuracy_reward": 0.5446450710296631,
+      "rewards/format_reward": 1.0,
+      "step": 82,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 267.9107360839844,
+      "epoch": 0.0031973496667822335,
+      "grad_norm": 1.8591300511545363,
+      "kl": 0.0150146484375,
+      "learning_rate": 9.999747758598746e-07,
+      "loss": 0.0006,
+      "reward": 1.6651928424835205,
+      "reward_std": 0.23238950967788696,
+      "rewards/accuracy_reward": 0.6901927590370178,
+      "rewards/format_reward": 0.8750000596046448,
+      "step": 83,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 170.98214721679688,
+      "epoch": 0.0032358719519241883,
+      "grad_norm": 3.460207937592012,
+      "kl": 0.0201416015625,
+      "learning_rate": 9.999741643930254e-07,
+      "loss": 0.0008,
+      "reward": 1.797253966331482,
+      "reward_std": 0.2454862743616104,
+      "rewards/accuracy_reward": 0.6508253216743469,
+      "rewards/format_reward": 1.0,
+      "step": 84,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 176.48214721679688,
+      "epoch": 0.0032743942370661427,
+      "grad_norm": 3.8333441326978015,
+      "kl": 0.01556396484375,
+      "learning_rate": 9.99973545603474e-07,
+      "loss": 0.0006,
+      "reward": 1.8520835638046265,
+      "reward_std": 0.13618475198745728,
+      "rewards/accuracy_reward": 0.7485119104385376,
+      "rewards/format_reward": 1.0,
+      "step": 85,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 142.21429443359375,
+      "epoch": 0.0033129165222080975,
+      "grad_norm": 5.546406170903967,
+      "kl": 0.018798828125,
+      "learning_rate": 9.999729194912288e-07,
+      "loss": 0.0007,
+      "reward": 1.512488603591919,
+      "reward_std": 0.15216389298439026,
+      "rewards/accuracy_reward": 0.4374885559082031,
+      "rewards/format_reward": 1.0,
+      "step": 86,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.0,
+      "completion_length": 135.8928680419922,
+      "epoch": 0.003351438807350052,
+      "grad_norm": 2.1938712459273173,
+      "kl": 0.0224609375,
+      "learning_rate": 9.999722860562995e-07,
+      "loss": 0.0009,
+      "reward": 1.9083168506622314,
+      "reward_std": 0.24992303550243378,
+      "rewards/accuracy_reward": 0.7904595136642456,
+      "rewards/format_reward": 1.0,
+      "step": 87,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 250.19644165039062,
+      "epoch": 0.0033899610924920066,
+      "grad_norm": 8.226109585653399,
+      "kl": 0.018310546875,
+      "learning_rate": 9.99971645298695e-07,
+      "loss": 0.0007,
+      "reward": 1.3736493587493896,
+      "reward_std": 0.31250062584877014,
+      "rewards/accuracy_reward": 0.42364928126335144,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 88,
+      "temporal_rewards": 0.357142835855484
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 220.37501525878906,
+      "epoch": 0.0034284833776339614,
+      "grad_norm": 1.0793537459382088,
+      "kl": 0.0166015625,
+      "learning_rate": 9.999709972184251e-07,
+      "loss": 0.0007,
+      "reward": 1.6861910820007324,
+      "reward_std": 0.17002300918102264,
+      "rewards/accuracy_reward": 0.571905255317688,
+      "rewards/format_reward": 1.0,
+      "step": 89,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 306.4464416503906,
+      "epoch": 0.0034670056627759157,
+      "grad_norm": 2.014793457696805,
+      "kl": 0.0150146484375,
+      "learning_rate": 9.99970341815499e-07,
+      "loss": 0.0006,
+      "reward": 1.4933110475540161,
+      "reward_std": 0.17901629209518433,
+      "rewards/accuracy_reward": 0.3933109641075134,
+      "rewards/format_reward": 1.0,
+      "step": 90,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 221.33929443359375,
+      "epoch": 0.0035055279479178705,
+      "grad_norm": 0.821835435471291,
+      "kl": 0.0206298828125,
+      "learning_rate": 9.999696790899263e-07,
+      "loss": 0.0008,
+      "reward": 1.6780954599380493,
+      "reward_std": 0.18597880005836487,
+      "rewards/accuracy_reward": 0.5959525108337402,
+      "rewards/format_reward": 0.9464285969734192,
+      "step": 91,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.5714285714285714,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 133.69644165039062,
+      "epoch": 0.0035440502330598253,
+      "grad_norm": 1.9159036924753614,
+      "kl": 0.0185546875,
+      "learning_rate": 9.999690090417167e-07,
+      "loss": 0.0007,
+      "reward": 1.908928632736206,
+      "reward_std": 0.15162892639636993,
+      "rewards/accuracy_reward": 0.7321428656578064,
+      "rewards/format_reward": 1.0,
+      "step": 92,
+      "temporal_rewards": 0.8571428656578064
+    },
+    {
+      "all_correct": 0.0,
+      "all_wrong": 0.0,
+      "completion_length": 272.51788330078125,
+      "epoch": 0.0035825725182017797,
+      "grad_norm": 2.5112506689696623,
+      "kl": 0.0167236328125,
+      "learning_rate": 9.999683316708803e-07,
+      "loss": 0.0007,
+      "reward": 1.4424163103103638,
+      "reward_std": 0.35725003480911255,
+      "rewards/accuracy_reward": 0.33705905079841614,
+      "rewards/format_reward": 1.0,
+      "step": 93,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.0,
+      "completion_length": 162.42857360839844,
+      "epoch": 0.0036210948033437345,
+      "grad_norm": 2.9519370343427767,
+      "kl": 0.0257568359375,
+      "learning_rate": 9.999676469774268e-07,
+      "loss": 0.001,
+      "reward": 1.7114182710647583,
+      "reward_std": 0.11487601697444916,
+      "rewards/accuracy_reward": 0.6310611963272095,
+      "rewards/format_reward": 1.0,
+      "step": 94,
+      "temporal_rewards": 0.5714285373687744
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 233.0357208251953,
+      "epoch": 0.003659617088485689,
+      "grad_norm": 2.4129406349857567,
+      "kl": 0.0164794921875,
+      "learning_rate": 9.999669549613662e-07,
+      "loss": 0.0007,
+      "reward": 1.651080846786499,
+      "reward_std": 0.29609203338623047,
+      "rewards/accuracy_reward": 0.5421521663665771,
+      "rewards/format_reward": 0.9821429252624512,
+      "step": 95,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.14285714285714285,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 176.33929443359375,
+      "epoch": 0.0036981393736276436,
+      "grad_norm": 2.4779580084833346,
+      "kl": 0.0201416015625,
+      "learning_rate": 9.999662556227086e-07,
+      "loss": 0.0008,
+      "reward": 1.4675571918487549,
+      "reward_std": 0.14850883185863495,
+      "rewards/accuracy_reward": 0.4675571322441101,
+      "rewards/format_reward": 1.0,
+      "step": 96,
+      "temporal_rewards": 0.4285714328289032
+    },
+    {
+      "all_correct": 0.2857142857142857,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 161.6428680419922,
+      "epoch": 0.0037366616587695984,
+      "grad_norm": 1.9659404766308382,
+      "kl": 0.0196533203125,
+      "learning_rate": 9.999655489614645e-07,
+      "loss": 0.0008,
+      "reward": 1.7886890172958374,
+      "reward_std": 0.09862305968999863,
+      "rewards/accuracy_reward": 0.6619032025337219,
+      "rewards/format_reward": 1.0,
+      "step": 97,
+      "temporal_rewards": 0.714285671710968
+    },
+    {
+      "all_correct": 0.5714285714285714,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 179.19644165039062,
+      "epoch": 0.0037751839439115528,
+      "grad_norm": 2.05557437418435,
+      "kl": 0.016357421875,
+      "learning_rate": 9.999648349776438e-07,
+      "loss": 0.0007,
+      "reward": 1.7678003311157227,
+      "reward_std": 0.06355559825897217,
+      "rewards/accuracy_reward": 0.6570857763290405,
+      "rewards/format_reward": 1.0,
+      "step": 98,
+      "temporal_rewards": 0.6428571343421936
+    },
+    {
+      "all_correct": 0.5714285714285714,
+      "all_wrong": 0.0,
+      "completion_length": 225.5535888671875,
+      "epoch": 0.0038137062290535075,
+      "grad_norm": 1.9682189342389496,
+      "kl": 0.0174560546875,
+      "learning_rate": 9.999641136712574e-07,
+      "loss": 0.0007,
+      "reward": 1.8416882753372192,
+      "reward_std": 0.17344672977924347,
+      "rewards/accuracy_reward": 0.6881167888641357,
+      "rewards/format_reward": 1.0,
+      "step": 99,
+      "temporal_rewards": 0.7857142686843872
+    },
+    {
+      "all_correct": 0.42857142857142855,
+      "all_wrong": 0.14285714285714285,
+      "completion_length": 214.48214721679688,
+      "epoch": 0.003852228514195462,
+      "grad_norm": 1.387767917535426,
+      "kl": 0.01708984375,
+      "learning_rate": 9.999633850423157e-07,
+      "loss": 0.0007,
+      "reward": 1.7011778354644775,
+      "reward_std": 0.10359158366918564,
+      "rewards/accuracy_reward": 0.5368921160697937,
+      "rewards/format_reward": 1.0,
+      "step": 100,
+      "temporal_rewards": 0.714285671710968
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 25959,
+  "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
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f8000e91d6e70d9c196be607065507c15e6558dae5f04550099f60e829a29a
+size 8504

last-checkpoint/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)