Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

global_step2000/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:de281302a90f821294b426edc9b1a72bf26c60e88000d19baebdffbe924ad238
+size 6033707356

global_step2000/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:b2f0826218571cba8c70dce58614b364cbe32c7709eab9dbadf23b69297c3b1f
+size 6033707356

global_step2000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfea6c1eb028deea660383a975a8c40deead00fbf2289cba0cec34a149b7580
+size 6033707356

global_step2000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f31cb7fd561337a72d840ab869301d1d5ac9d0fc30fbea3619197d5f15a8427
+size 6033707356

global_step2000/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d9ed5544314d41e3dc5f36f025fa34e883603f64fd3167625cb0efbc4de4db9
+size 6033707356

global_step2000/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503e8ed2e065f718ece8c366c1b22d50aa3e076bc57caff4f4312660ec973cac
+size 6033707356

global_step2000/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c29a4d217508ec1f741313a3dc4be48c78ce83827646279f702655e58a302a
+size 6033707356

global_step2000/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cce15930a6f4c70673bb05cf0390639921ca13bf10a26cd12a58a234a0b0f9
+size 6033707356

global_step2000/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5c1dfe01e91cff4711947609595613360895eefa3b15ac79d3bf8f6e01a56d5
+size 202052

global_step2000/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b054a27eb680e2f5c2ebc46d350acc90ff3d5354429cacd35ddc73082d433059
+size 201988

global_step2000/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b2036d1a18b36740d151d2f0d86c5cbfb868aac288c42e02b73d940a9152b15
+size 201988

global_step2000/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9660f1173f63d68c8c7f594b967fed93b705da1f532463eefef2e8656bad867
+size 201988

global_step2000/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5266857b8ddfc3937afca875cfb48d1ddf4306c6f49b462ddecc4a3d8585d70f
+size 201988

global_step2000/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:559ad1b51fa356bc1a693ca49f21fb93a7982cabc9e758dab5ff542a3c076172
+size 201988

global_step2000/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3de164ab647d7e83b416a4a6b1aaf2e0dd1b7ce7b3d2794583da4906b0dda3c
+size 201988

global_step2000/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70610ce5c8f2c3046efabe2ff025fec1615e03d3b0739ea1ebc7b045959e1c61
+size 201988

latest

@@ -0,0 +1 @@
+global_step2000

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6252722de72537911c8e876efde5ce9e48c7f79304161d521387e6685c5ba673
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43df4ceac524226754edaa800168334c3896e26f41ca201e585aee16444ba516
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 196096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:955b895101e13c81ba510512313a06782795770a0bf998c90f718166d25f1664
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:096e351ace65ff91008be171a45173ed6369cc639fce73a288f671041e24b0ec
+size 15984

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21c61b1a7e793bbdec183de3b52da90042305234bc7e5887986655cd3fc2192
+size 15984

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:348742498d81780506d9760c655a7a7555185b5fbd70a7ae296d88fd9aeecd84
+size 15984

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399c4700dab9ae7b754110ce307fb7e26e22cb49b5bb233c435f0f12b77c202f
+size 15984

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:864ea2379cc907eb4189c52706cb978150d9c26e18abf74679590729a8f0c8e8
+size 15984

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25755ba07299ee6ff45936dd04df329596319c9f8095af71e6f3a219e7543e26
+size 15984

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:908f018cd701ed629c41299726da4a25f202f20a1d4bc2075a2266ed4013db3a
+size 15984

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f026df4fdf15eb8c9c80228dca3957c9abddca2810442dff8b4814a82b3752
+size 1064

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
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01599987200102399,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 7.999936000511996e-05,
+      "grad_norm": 4.414881453815827,
+      "learning_rate": 7.199424046076314e-09,
+      "loss": 0.5441,
+      "step": 10
+    },
+    {
+      "epoch": 0.00015999872001023991,
+      "grad_norm": 4.004957247533114,
+      "learning_rate": 1.519878409727222e-08,
+      "loss": 0.5353,
+      "step": 20
+    },
+    {
+      "epoch": 0.00023999808001535987,
+      "grad_norm": 4.889790729834478,
+      "learning_rate": 2.3198144148468124e-08,
+      "loss": 0.537,
+      "step": 30
+    },
+    {
+      "epoch": 0.00031999744002047983,
+      "grad_norm": 3.7138301639437508,
+      "learning_rate": 3.119750419966403e-08,
+      "loss": 0.5488,
+      "step": 40
+    },
+    {
+      "epoch": 0.0003999968000255998,
+      "grad_norm": 4.208028943214464,
+      "learning_rate": 3.919686425085993e-08,
+      "loss": 0.5557,
+      "step": 50
+    },
+    {
+      "epoch": 0.00047999616003071974,
+      "grad_norm": 4.326896533998126,
+      "learning_rate": 4.719622430205584e-08,
+      "loss": 0.5061,
+      "step": 60
+    },
+    {
+      "epoch": 0.0005599955200358397,
+      "grad_norm": 7.1723877700496415,
+      "learning_rate": 5.519558435325175e-08,
+      "loss": 0.5193,
+      "step": 70
+    },
+    {
+      "epoch": 0.0006399948800409597,
+      "grad_norm": 3.892238785520058,
+      "learning_rate": 6.319494440444764e-08,
+      "loss": 0.5311,
+      "step": 80
+    },
+    {
+      "epoch": 0.0007199942400460796,
+      "grad_norm": 3.4517472540795513,
+      "learning_rate": 7.119430445564356e-08,
+      "loss": 0.5232,
+      "step": 90
+    },
+    {
+      "epoch": 0.0007999936000511996,
+      "grad_norm": 4.094057558667446,
+      "learning_rate": 7.919366450683946e-08,
+      "loss": 0.5225,
+      "step": 100
+    },
+    {
+      "epoch": 0.0008799929600563195,
+      "grad_norm": 3.4395682865399144,
+      "learning_rate": 8.719302455803536e-08,
+      "loss": 0.5371,
+      "step": 110
+    },
+    {
+      "epoch": 0.0009599923200614395,
+      "grad_norm": 3.7029712275218682,
+      "learning_rate": 9.519238460923127e-08,
+      "loss": 0.5305,
+      "step": 120
+    },
+    {
+      "epoch": 0.0010399916800665594,
+      "grad_norm": 3.493027269180126,
+      "learning_rate": 1.0319174466042718e-07,
+      "loss": 0.5167,
+      "step": 130
+    },
+    {
+      "epoch": 0.0011199910400716794,
+      "grad_norm": 3.480790725115363,
+      "learning_rate": 1.1119110471162308e-07,
+      "loss": 0.5543,
+      "step": 140
+    },
+    {
+      "epoch": 0.0011999904000767993,
+      "grad_norm": 3.0350778792458564,
+      "learning_rate": 1.1919046476281897e-07,
+      "loss": 0.5188,
+      "step": 150
+    },
+    {
+      "epoch": 0.0012799897600819193,
+      "grad_norm": 2.7703962024693216,
+      "learning_rate": 1.271898248140149e-07,
+      "loss": 0.5176,
+      "step": 160
+    },
+    {
+      "epoch": 0.0013599891200870393,
+      "grad_norm": 2.7312812150288277,
+      "learning_rate": 1.351891848652108e-07,
+      "loss": 0.5206,
+      "step": 170
+    },
+    {
+      "epoch": 0.0014399884800921593,
+      "grad_norm": 2.6772442085163837,
+      "learning_rate": 1.431885449164067e-07,
+      "loss": 0.5187,
+      "step": 180
+    },
+    {
+      "epoch": 0.0015199878400972793,
+      "grad_norm": 2.6017371604025503,
+      "learning_rate": 1.5118790496760262e-07,
+      "loss": 0.4858,
+      "step": 190
+    },
+    {
+      "epoch": 0.0015999872001023993,
+      "grad_norm": 2.361921882047865,
+      "learning_rate": 1.5918726501879854e-07,
+      "loss": 0.4965,
+      "step": 200
+    },
+    {
+      "epoch": 0.0016799865601075192,
+      "grad_norm": 1.9949603945902301,
+      "learning_rate": 1.6718662506999443e-07,
+      "loss": 0.49,
+      "step": 210
+    },
+    {
+      "epoch": 0.001759985920112639,
+      "grad_norm": 1.689017850332906,
+      "learning_rate": 1.7518598512119031e-07,
+      "loss": 0.4474,
+      "step": 220
+    },
+    {
+      "epoch": 0.001839985280117759,
+      "grad_norm": 1.7526108484730667,
+      "learning_rate": 1.8318534517238623e-07,
+      "loss": 0.4758,
+      "step": 230
+    },
+    {
+      "epoch": 0.001919984640122879,
+      "grad_norm": 1.6619250196852287,
+      "learning_rate": 1.9118470522358212e-07,
+      "loss": 0.4551,
+      "step": 240
+    },
+    {
+      "epoch": 0.001999984000127999,
+      "grad_norm": 1.4244411983222107,
+      "learning_rate": 1.9918406527477803e-07,
+      "loss": 0.4666,
+      "step": 250
+    },
+    {
+      "epoch": 0.0020799833601331187,
+      "grad_norm": 1.4091371713945773,
+      "learning_rate": 2.0718342532597392e-07,
+      "loss": 0.4744,
+      "step": 260
+    },
+    {
+      "epoch": 0.002159982720138239,
+      "grad_norm": 1.4037698231377602,
+      "learning_rate": 2.1518278537716986e-07,
+      "loss": 0.4577,
+      "step": 270
+    },
+    {
+      "epoch": 0.0022399820801433587,
+      "grad_norm": 1.1233973407058262,
+      "learning_rate": 2.2318214542836575e-07,
+      "loss": 0.4442,
+      "step": 280
+    },
+    {
+      "epoch": 0.002319981440148479,
+      "grad_norm": 1.0934034827825632,
+      "learning_rate": 2.3118150547956164e-07,
+      "loss": 0.4746,
+      "step": 290
+    },
+    {
+      "epoch": 0.0023999808001535987,
+      "grad_norm": 0.9547032856231036,
+      "learning_rate": 2.3918086553075753e-07,
+      "loss": 0.4631,
+      "step": 300
+    },
+    {
+      "epoch": 0.002479980160158719,
+      "grad_norm": 1.011447249716743,
+      "learning_rate": 2.4718022558195345e-07,
+      "loss": 0.4359,
+      "step": 310
+    },
+    {
+      "epoch": 0.0025599795201638386,
+      "grad_norm": 0.7506687829382205,
+      "learning_rate": 2.5517958563314936e-07,
+      "loss": 0.4554,
+      "step": 320
+    },
+    {
+      "epoch": 0.002639978880168959,
+      "grad_norm": 0.8268141903301145,
+      "learning_rate": 2.631789456843453e-07,
+      "loss": 0.4444,
+      "step": 330
+    },
+    {
+      "epoch": 0.0027199782401740786,
+      "grad_norm": 0.9120933866995852,
+      "learning_rate": 2.711783057355412e-07,
+      "loss": 0.4662,
+      "step": 340
+    },
+    {
+      "epoch": 0.0027999776001791984,
+      "grad_norm": 0.9481570868182263,
+      "learning_rate": 2.791776657867371e-07,
+      "loss": 0.4677,
+      "step": 350
+    },
+    {
+      "epoch": 0.0028799769601843186,
+      "grad_norm": 0.8010445040150771,
+      "learning_rate": 2.8717702583793297e-07,
+      "loss": 0.4196,
+      "step": 360
+    },
+    {
+      "epoch": 0.0029599763201894383,
+      "grad_norm": 0.8670839473253033,
+      "learning_rate": 2.951763858891289e-07,
+      "loss": 0.4492,
+      "step": 370
+    },
+    {
+      "epoch": 0.0030399756801945585,
+      "grad_norm": 0.8536232676044045,
+      "learning_rate": 3.031757459403248e-07,
+      "loss": 0.4375,
+      "step": 380
+    },
+    {
+      "epoch": 0.0031199750401996783,
+      "grad_norm": 0.8135677817452803,
+      "learning_rate": 3.111751059915207e-07,
+      "loss": 0.438,
+      "step": 390
+    },
+    {
+      "epoch": 0.0031999744002047985,
+      "grad_norm": 0.9667962048008838,
+      "learning_rate": 3.191744660427166e-07,
+      "loss": 0.4348,
+      "step": 400
+    },
+    {
+      "epoch": 0.0032799737602099183,
+      "grad_norm": 0.885059264680228,
+      "learning_rate": 3.271738260939125e-07,
+      "loss": 0.4295,
+      "step": 410
+    },
+    {
+      "epoch": 0.0033599731202150385,
+      "grad_norm": 0.7112007856245484,
+      "learning_rate": 3.3517318614510846e-07,
+      "loss": 0.4412,
+      "step": 420
+    },
+    {
+      "epoch": 0.0034399724802201583,
+      "grad_norm": 0.9486242885147141,
+      "learning_rate": 3.431725461963043e-07,
+      "loss": 0.4357,
+      "step": 430
+    },
+    {
+      "epoch": 0.003519971840225278,
+      "grad_norm": 0.7792187180449996,
+      "learning_rate": 3.5117190624750024e-07,
+      "loss": 0.4053,
+      "step": 440
+    },
+    {
+      "epoch": 0.0035999712002303982,
+      "grad_norm": 0.8013118911013118,
+      "learning_rate": 3.591712662986961e-07,
+      "loss": 0.4526,
+      "step": 450
+    },
+    {
+      "epoch": 0.003679970560235518,
+      "grad_norm": 0.9290353407648725,
+      "learning_rate": 3.6717062634989207e-07,
+      "loss": 0.4394,
+      "step": 460
+    },
+    {
+      "epoch": 0.003759969920240638,
+      "grad_norm": 0.7440275824040646,
+      "learning_rate": 3.7516998640108793e-07,
+      "loss": 0.4354,
+      "step": 470
+    },
+    {
+      "epoch": 0.003839969280245758,
+      "grad_norm": 0.6661735557442742,
+      "learning_rate": 3.8316934645228385e-07,
+      "loss": 0.4132,
+      "step": 480
+    },
+    {
+      "epoch": 0.003919968640250878,
+      "grad_norm": 0.80714967397643,
+      "learning_rate": 3.9116870650347976e-07,
+      "loss": 0.4247,
+      "step": 490
+    },
+    {
+      "epoch": 0.003999968000255998,
+      "grad_norm": 0.7269691108846945,
+      "learning_rate": 3.9916806655467563e-07,
+      "loss": 0.4308,
+      "step": 500
+    },
+    {
+      "epoch": 0.004079967360261118,
+      "grad_norm": 0.8112092339496537,
+      "learning_rate": 4.071674266058716e-07,
+      "loss": 0.4215,
+      "step": 510
+    },
+    {
+      "epoch": 0.0041599667202662375,
+      "grad_norm": 0.8465738727092779,
+      "learning_rate": 4.1516678665706746e-07,
+      "loss": 0.4438,
+      "step": 520
+    },
+    {
+      "epoch": 0.004239966080271358,
+      "grad_norm": 0.7947114246478345,
+      "learning_rate": 4.2316614670826337e-07,
+      "loss": 0.402,
+      "step": 530
+    },
+    {
+      "epoch": 0.004319965440276478,
+      "grad_norm": 0.771445835897062,
+      "learning_rate": 4.311655067594593e-07,
+      "loss": 0.4434,
+      "step": 540
+    },
+    {
+      "epoch": 0.004399964800281598,
+      "grad_norm": 0.7143580000434352,
+      "learning_rate": 4.3916486681065515e-07,
+      "loss": 0.4227,
+      "step": 550
+    },
+    {
+      "epoch": 0.004479964160286717,
+      "grad_norm": 0.7487773075552359,
+      "learning_rate": 4.471642268618511e-07,
+      "loss": 0.438,
+      "step": 560
+    },
+    {
+      "epoch": 0.004559963520291838,
+      "grad_norm": 0.7373810653849879,
+      "learning_rate": 4.55163586913047e-07,
+      "loss": 0.4288,
+      "step": 570
+    },
+    {
+      "epoch": 0.004639962880296958,
+      "grad_norm": 0.7104505393064982,
+      "learning_rate": 4.631629469642429e-07,
+      "loss": 0.4462,
+      "step": 580
+    },
+    {
+      "epoch": 0.004719962240302078,
+      "grad_norm": 0.6996674322090365,
+      "learning_rate": 4.7116230701543876e-07,
+      "loss": 0.4263,
+      "step": 590
+    },
+    {
+      "epoch": 0.004799961600307197,
+      "grad_norm": 0.779468888606517,
+      "learning_rate": 4.791616670666347e-07,
+      "loss": 0.4378,
+      "step": 600
+    },
+    {
+      "epoch": 0.0048799609603123175,
+      "grad_norm": 0.6348456379271163,
+      "learning_rate": 4.871610271178306e-07,
+      "loss": 0.4098,
+      "step": 610
+    },
+    {
+      "epoch": 0.004959960320317438,
+      "grad_norm": 0.6384341588537313,
+      "learning_rate": 4.951603871690265e-07,
+      "loss": 0.4489,
+      "step": 620
+    },
+    {
+      "epoch": 0.005039959680322557,
+      "grad_norm": 0.6779051066808497,
+      "learning_rate": 5.031597472202224e-07,
+      "loss": 0.4522,
+      "step": 630
+    },
+    {
+      "epoch": 0.005119959040327677,
+      "grad_norm": 0.7405337420145796,
+      "learning_rate": 5.111591072714183e-07,
+      "loss": 0.4248,
+      "step": 640
+    },
+    {
+      "epoch": 0.0051999584003327975,
+      "grad_norm": 0.6915688533513078,
+      "learning_rate": 5.191584673226143e-07,
+      "loss": 0.4129,
+      "step": 650
+    },
+    {
+      "epoch": 0.005279957760337918,
+      "grad_norm": 0.6044444399034763,
+      "learning_rate": 5.271578273738101e-07,
+      "loss": 0.4237,
+      "step": 660
+    },
+    {
+      "epoch": 0.005359957120343037,
+      "grad_norm": 0.7401624173362278,
+      "learning_rate": 5.351571874250061e-07,
+      "loss": 0.4216,
+      "step": 670
+    },
+    {
+      "epoch": 0.005439956480348157,
+      "grad_norm": 0.7496141168534413,
+      "learning_rate": 5.43156547476202e-07,
+      "loss": 0.4268,
+      "step": 680
+    },
+    {
+      "epoch": 0.005519955840353277,
+      "grad_norm": 0.730614366570662,
+      "learning_rate": 5.511559075273978e-07,
+      "loss": 0.4589,
+      "step": 690
+    },
+    {
+      "epoch": 0.005599955200358397,
+      "grad_norm": 0.7836211351094068,
+      "learning_rate": 5.591552675785937e-07,
+      "loss": 0.4176,
+      "step": 700
+    },
+    {
+      "epoch": 0.005679954560363517,
+      "grad_norm": 0.6648189022606215,
+      "learning_rate": 5.671546276297896e-07,
+      "loss": 0.4274,
+      "step": 710
+    },
+    {
+      "epoch": 0.005759953920368637,
+      "grad_norm": 0.6607901995290275,
+      "learning_rate": 5.751539876809856e-07,
+      "loss": 0.428,
+      "step": 720
+    },
+    {
+      "epoch": 0.005839953280373757,
+      "grad_norm": 0.8422142881250906,
+      "learning_rate": 5.831533477321815e-07,
+      "loss": 0.4206,
+      "step": 730
+    },
+    {
+      "epoch": 0.005919952640378877,
+      "grad_norm": 0.8636103630308042,
+      "learning_rate": 5.911527077833774e-07,
+      "loss": 0.4384,
+      "step": 740
+    },
+    {
+      "epoch": 0.005999952000383997,
+      "grad_norm": 0.7020283376881055,
+      "learning_rate": 5.991520678345733e-07,
+      "loss": 0.4336,
+      "step": 750
+    },
+    {
+      "epoch": 0.006079951360389117,
+      "grad_norm": 0.6637768636661737,
+      "learning_rate": 6.071514278857692e-07,
+      "loss": 0.421,
+      "step": 760
+    },
+    {
+      "epoch": 0.006159950720394236,
+      "grad_norm": 0.6720228370970702,
+      "learning_rate": 6.151507879369651e-07,
+      "loss": 0.4425,
+      "step": 770
+    },
+    {
+      "epoch": 0.006239950080399357,
+      "grad_norm": 0.7915308024009126,
+      "learning_rate": 6.231501479881609e-07,
+      "loss": 0.4665,
+      "step": 780
+    },
+    {
+      "epoch": 0.006319949440404477,
+      "grad_norm": 0.7005483141808596,
+      "learning_rate": 6.311495080393569e-07,
+      "loss": 0.4371,
+      "step": 790
+    },
+    {
+      "epoch": 0.006399948800409597,
+      "grad_norm": 0.7085842808188052,
+      "learning_rate": 6.391488680905528e-07,
+      "loss": 0.4481,
+      "step": 800
+    },
+    {
+      "epoch": 0.006479948160414716,
+      "grad_norm": 0.797364113205394,
+      "learning_rate": 6.471482281417488e-07,
+      "loss": 0.43,
+      "step": 810
+    },
+    {
+      "epoch": 0.0065599475204198366,
+      "grad_norm": 0.7769920944189029,
+      "learning_rate": 6.551475881929446e-07,
+      "loss": 0.4421,
+      "step": 820
+    },
+    {
+      "epoch": 0.006639946880424957,
+      "grad_norm": 0.7190098449382926,
+      "learning_rate": 6.631469482441405e-07,
+      "loss": 0.4524,
+      "step": 830
+    },
+    {
+      "epoch": 0.006719946240430077,
+      "grad_norm": 0.8999089940382301,
+      "learning_rate": 6.711463082953363e-07,
+      "loss": 0.4327,
+      "step": 840
+    },
+    {
+      "epoch": 0.006799945600435196,
+      "grad_norm": 0.8071258672281636,
+      "learning_rate": 6.791456683465323e-07,
+      "loss": 0.3999,
+      "step": 850
+    },
+    {
+      "epoch": 0.0068799449604403165,
+      "grad_norm": 0.9718244104757909,
+      "learning_rate": 6.871450283977283e-07,
+      "loss": 0.4109,
+      "step": 860
+    },
+    {
+      "epoch": 0.006959944320445437,
+      "grad_norm": 0.7260805899057289,
+      "learning_rate": 6.951443884489241e-07,
+      "loss": 0.4254,
+      "step": 870
+    },
+    {
+      "epoch": 0.007039943680450556,
+      "grad_norm": 0.6793848246836304,
+      "learning_rate": 7.031437485001201e-07,
+      "loss": 0.4168,
+      "step": 880
+    },
+    {
+      "epoch": 0.007119943040455676,
+      "grad_norm": 0.8220405330990818,
+      "learning_rate": 7.11143108551316e-07,
+      "loss": 0.4368,
+      "step": 890
+    },
+    {
+      "epoch": 0.0071999424004607964,
+      "grad_norm": 0.8650021092848164,
+      "learning_rate": 7.191424686025118e-07,
+      "loss": 0.4336,
+      "step": 900
+    },
+    {
+      "epoch": 0.007279941760465917,
+      "grad_norm": 0.6667689577948444,
+      "learning_rate": 7.271418286537078e-07,
+      "loss": 0.4325,
+      "step": 910
+    },
+    {
+      "epoch": 0.007359941120471036,
+      "grad_norm": 0.6443211014509481,
+      "learning_rate": 7.351411887049036e-07,
+      "loss": 0.443,
+      "step": 920
+    },
+    {
+      "epoch": 0.007439940480476156,
+      "grad_norm": 0.6067913066251965,
+      "learning_rate": 7.431405487560996e-07,
+      "loss": 0.4095,
+      "step": 930
+    },
+    {
+      "epoch": 0.007519939840481276,
+      "grad_norm": 0.6935512372810877,
+      "learning_rate": 7.511399088072954e-07,
+      "loss": 0.4272,
+      "step": 940
+    },
+    {
+      "epoch": 0.007599939200486396,
+      "grad_norm": 0.6599113657719949,
+      "learning_rate": 7.591392688584914e-07,
+      "loss": 0.3942,
+      "step": 950
+    },
+    {
+      "epoch": 0.007679938560491516,
+      "grad_norm": 0.611225655896161,
+      "learning_rate": 7.671386289096873e-07,
+      "loss": 0.4451,
+      "step": 960
+    },
+    {
+      "epoch": 0.007759937920496636,
+      "grad_norm": 0.757015652343119,
+      "learning_rate": 7.751379889608831e-07,
+      "loss": 0.4059,
+      "step": 970
+    },
+    {
+      "epoch": 0.007839937280501755,
+      "grad_norm": 0.8456384517410107,
+      "learning_rate": 7.831373490120791e-07,
+      "loss": 0.4278,
+      "step": 980
+    },
+    {
+      "epoch": 0.007919936640506876,
+      "grad_norm": 0.7996016208371923,
+      "learning_rate": 7.911367090632751e-07,
+      "loss": 0.4536,
+      "step": 990
+    },
+    {
+      "epoch": 0.007999936000511996,
+      "grad_norm": 0.6228736248515305,
+      "learning_rate": 7.991360691144709e-07,
+      "loss": 0.3969,
+      "step": 1000
+    },
+    {
+      "epoch": 0.008079935360517116,
+      "grad_norm": 0.6440105424946402,
+      "learning_rate": 8.071354291656668e-07,
+      "loss": 0.4307,
+      "step": 1010
+    },
+    {
+      "epoch": 0.008159934720522236,
+      "grad_norm": 0.6636370756757088,
+      "learning_rate": 8.151347892168628e-07,
+      "loss": 0.4019,
+      "step": 1020
+    },
+    {
+      "epoch": 0.008239934080527356,
+      "grad_norm": 0.6534728964626215,
+      "learning_rate": 8.231341492680586e-07,
+      "loss": 0.4357,
+      "step": 1030
+    },
+    {
+      "epoch": 0.008319933440532475,
+      "grad_norm": 0.6854238349847609,
+      "learning_rate": 8.311335093192545e-07,
+      "loss": 0.4156,
+      "step": 1040
+    },
+    {
+      "epoch": 0.008399932800537595,
+      "grad_norm": 0.7692797686595098,
+      "learning_rate": 8.391328693704504e-07,
+      "loss": 0.4364,
+      "step": 1050
+    },
+    {
+      "epoch": 0.008479932160542715,
+      "grad_norm": 0.6892139807862941,
+      "learning_rate": 8.471322294216464e-07,
+      "loss": 0.4595,
+      "step": 1060
+    },
+    {
+      "epoch": 0.008559931520547836,
+      "grad_norm": 0.6786670330601587,
+      "learning_rate": 8.551315894728423e-07,
+      "loss": 0.4207,
+      "step": 1070
+    },
+    {
+      "epoch": 0.008639930880552956,
+      "grad_norm": 0.6118366771253826,
+      "learning_rate": 8.631309495240381e-07,
+      "loss": 0.4186,
+      "step": 1080
+    },
+    {
+      "epoch": 0.008719930240558076,
+      "grad_norm": 0.7157718863255984,
+      "learning_rate": 8.711303095752341e-07,
+      "loss": 0.4412,
+      "step": 1090
+    },
+    {
+      "epoch": 0.008799929600563196,
+      "grad_norm": 0.7102096103999658,
+      "learning_rate": 8.791296696264299e-07,
+      "loss": 0.4205,
+      "step": 1100
+    },
+    {
+      "epoch": 0.008879928960568315,
+      "grad_norm": 0.6326552697725677,
+      "learning_rate": 8.871290296776258e-07,
+      "loss": 0.4161,
+      "step": 1110
+    },
+    {
+      "epoch": 0.008959928320573435,
+      "grad_norm": 0.7455469536196851,
+      "learning_rate": 8.951283897288219e-07,
+      "loss": 0.4259,
+      "step": 1120
+    },
+    {
+      "epoch": 0.009039927680578555,
+      "grad_norm": 0.8219540514047248,
+      "learning_rate": 9.031277497800177e-07,
+      "loss": 0.4423,
+      "step": 1130
+    },
+    {
+      "epoch": 0.009119927040583675,
+      "grad_norm": 0.6428846698552027,
+      "learning_rate": 9.111271098312136e-07,
+      "loss": 0.432,
+      "step": 1140
+    },
+    {
+      "epoch": 0.009199926400588795,
+      "grad_norm": 0.7959015617833209,
+      "learning_rate": 9.191264698824094e-07,
+      "loss": 0.4374,
+      "step": 1150
+    },
+    {
+      "epoch": 0.009279925760593916,
+      "grad_norm": 0.722690696817927,
+      "learning_rate": 9.271258299336054e-07,
+      "loss": 0.4177,
+      "step": 1160
+    },
+    {
+      "epoch": 0.009359925120599036,
+      "grad_norm": 0.7583146312532495,
+      "learning_rate": 9.351251899848013e-07,
+      "loss": 0.4349,
+      "step": 1170
+    },
+    {
+      "epoch": 0.009439924480604156,
+      "grad_norm": 0.8841341873240007,
+      "learning_rate": 9.431245500359971e-07,
+      "loss": 0.4323,
+      "step": 1180
+    },
+    {
+      "epoch": 0.009519923840609274,
+      "grad_norm": 0.6844990736142492,
+      "learning_rate": 9.511239100871932e-07,
+      "loss": 0.4195,
+      "step": 1190
+    },
+    {
+      "epoch": 0.009599923200614395,
+      "grad_norm": 0.7129122863481299,
+      "learning_rate": 9.59123270138389e-07,
+      "loss": 0.4088,
+      "step": 1200
+    },
+    {
+      "epoch": 0.009679922560619515,
+      "grad_norm": 0.6532760834208395,
+      "learning_rate": 9.67122630189585e-07,
+      "loss": 0.3969,
+      "step": 1210
+    },
+    {
+      "epoch": 0.009759921920624635,
+      "grad_norm": 0.7563260927255472,
+      "learning_rate": 9.75121990240781e-07,
+      "loss": 0.4075,
+      "step": 1220
+    },
+    {
+      "epoch": 0.009839921280629755,
+      "grad_norm": 0.7704505024635662,
+      "learning_rate": 9.831213502919768e-07,
+      "loss": 0.3981,
+      "step": 1230
+    },
+    {
+      "epoch": 0.009919920640634875,
+      "grad_norm": 0.7056792723024738,
+      "learning_rate": 9.911207103431725e-07,
+      "loss": 0.4223,
+      "step": 1240
+    },
+    {
+      "epoch": 0.009999920000639996,
+      "grad_norm": 0.750390399783068,
+      "learning_rate": 9.991200703943684e-07,
+      "loss": 0.4102,
+      "step": 1250
+    },
+    {
+      "epoch": 0.010079919360645114,
+      "grad_norm": 0.7529460057363149,
+      "learning_rate": 1.0071194304455646e-06,
+      "loss": 0.4278,
+      "step": 1260
+    },
+    {
+      "epoch": 0.010159918720650234,
+      "grad_norm": 1.041695148553965,
+      "learning_rate": 1.0151187904967603e-06,
+      "loss": 0.4261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.010239918080655355,
+      "grad_norm": 0.8098838670880232,
+      "learning_rate": 1.0231181505479562e-06,
+      "loss": 0.4163,
+      "step": 1280
+    },
+    {
+      "epoch": 0.010319917440660475,
+      "grad_norm": 0.7139180273227849,
+      "learning_rate": 1.0311175105991523e-06,
+      "loss": 0.4139,
+      "step": 1290
+    },
+    {
+      "epoch": 0.010399916800665595,
+      "grad_norm": 0.7293628900497775,
+      "learning_rate": 1.039116870650348e-06,
+      "loss": 0.4139,
+      "step": 1300
+    },
+    {
+      "epoch": 0.010479916160670715,
+      "grad_norm": 3.9899125178456276,
+      "learning_rate": 1.047116230701544e-06,
+      "loss": 0.4352,
+      "step": 1310
+    },
+    {
+      "epoch": 0.010559915520675835,
+      "grad_norm": 0.741428608083807,
+      "learning_rate": 1.0551155907527398e-06,
+      "loss": 0.4487,
+      "step": 1320
+    },
+    {
+      "epoch": 0.010639914880680954,
+      "grad_norm": 0.7645959836257802,
+      "learning_rate": 1.0631149508039358e-06,
+      "loss": 0.4509,
+      "step": 1330
+    },
+    {
+      "epoch": 0.010719914240686074,
+      "grad_norm": 0.6630163901596575,
+      "learning_rate": 1.0711143108551317e-06,
+      "loss": 0.422,
+      "step": 1340
+    },
+    {
+      "epoch": 0.010799913600691194,
+      "grad_norm": 0.7653242364061862,
+      "learning_rate": 1.0791136709063276e-06,
+      "loss": 0.4047,
+      "step": 1350
+    },
+    {
+      "epoch": 0.010879912960696314,
+      "grad_norm": 0.6952138151449674,
+      "learning_rate": 1.0871130309575235e-06,
+      "loss": 0.424,
+      "step": 1360
+    },
+    {
+      "epoch": 0.010959912320701435,
+      "grad_norm": 0.8400358998787617,
+      "learning_rate": 1.0951123910087194e-06,
+      "loss": 0.4329,
+      "step": 1370
+    },
+    {
+      "epoch": 0.011039911680706555,
+      "grad_norm": 0.7959368745719518,
+      "learning_rate": 1.1031117510599153e-06,
+      "loss": 0.4296,
+      "step": 1380
+    },
+    {
+      "epoch": 0.011119911040711675,
+      "grad_norm": 0.7182831330712102,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 0.4053,
+      "step": 1390
+    },
+    {
+      "epoch": 0.011199910400716794,
+      "grad_norm": 0.7631459457678664,
+      "learning_rate": 1.1191104711623072e-06,
+      "loss": 0.4174,
+      "step": 1400
+    },
+    {
+      "epoch": 0.011279909760721914,
+      "grad_norm": 0.6904060292491346,
+      "learning_rate": 1.127109831213503e-06,
+      "loss": 0.4262,
+      "step": 1410
+    },
+    {
+      "epoch": 0.011359909120727034,
+      "grad_norm": 0.7154968430224656,
+      "learning_rate": 1.1351091912646988e-06,
+      "loss": 0.4116,
+      "step": 1420
+    },
+    {
+      "epoch": 0.011439908480732154,
+      "grad_norm": 0.6430506977204669,
+      "learning_rate": 1.143108551315895e-06,
+      "loss": 0.3985,
+      "step": 1430
+    },
+    {
+      "epoch": 0.011519907840737274,
+      "grad_norm": 0.6060536937789834,
+      "learning_rate": 1.1511079113670908e-06,
+      "loss": 0.4366,
+      "step": 1440
+    },
+    {
+      "epoch": 0.011599907200742395,
+      "grad_norm": 0.7070045694797042,
+      "learning_rate": 1.1591072714182865e-06,
+      "loss": 0.3951,
+      "step": 1450
+    },
+    {
+      "epoch": 0.011679906560747515,
+      "grad_norm": 0.6799481270205386,
+      "learning_rate": 1.1671066314694824e-06,
+      "loss": 0.4277,
+      "step": 1460
+    },
+    {
+      "epoch": 0.011759905920752633,
+      "grad_norm": 0.7706688131579046,
+      "learning_rate": 1.1751059915206786e-06,
+      "loss": 0.4106,
+      "step": 1470
+    },
+    {
+      "epoch": 0.011839905280757753,
+      "grad_norm": 0.7659401655636618,
+      "learning_rate": 1.1831053515718743e-06,
+      "loss": 0.4147,
+      "step": 1480
+    },
+    {
+      "epoch": 0.011919904640762874,
+      "grad_norm": 0.7880351649260696,
+      "learning_rate": 1.1911047116230702e-06,
+      "loss": 0.4018,
+      "step": 1490
+    },
+    {
+      "epoch": 0.011999904000767994,
+      "grad_norm": 0.6643952514129879,
+      "learning_rate": 1.1991040716742661e-06,
+      "loss": 0.4225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.012079903360773114,
+      "grad_norm": 0.7410891062680932,
+      "learning_rate": 1.207103431725462e-06,
+      "loss": 0.4235,
+      "step": 1510
+    },
+    {
+      "epoch": 0.012159902720778234,
+      "grad_norm": 0.6702465025094532,
+      "learning_rate": 1.215102791776658e-06,
+      "loss": 0.4485,
+      "step": 1520
+    },
+    {
+      "epoch": 0.012239902080783354,
+      "grad_norm": 0.72511805103151,
+      "learning_rate": 1.2231021518278539e-06,
+      "loss": 0.4075,
+      "step": 1530
+    },
+    {
+      "epoch": 0.012319901440788473,
+      "grad_norm": 0.7364457263640842,
+      "learning_rate": 1.2311015118790498e-06,
+      "loss": 0.4209,
+      "step": 1540
+    },
+    {
+      "epoch": 0.012399900800793593,
+      "grad_norm": 0.6760801533876919,
+      "learning_rate": 1.2391008719302457e-06,
+      "loss": 0.4153,
+      "step": 1550
+    },
+    {
+      "epoch": 0.012479900160798713,
+      "grad_norm": 1.329240774622819,
+      "learning_rate": 1.2471002319814416e-06,
+      "loss": 0.4569,
+      "step": 1560
+    },
+    {
+      "epoch": 0.012559899520803833,
+      "grad_norm": 0.7197695590369367,
+      "learning_rate": 1.2550995920326375e-06,
+      "loss": 0.4148,
+      "step": 1570
+    },
+    {
+      "epoch": 0.012639898880808954,
+      "grad_norm": 0.7197146321929337,
+      "learning_rate": 1.2630989520838332e-06,
+      "loss": 0.4309,
+      "step": 1580
+    },
+    {
+      "epoch": 0.012719898240814074,
+      "grad_norm": 0.6941046794760515,
+      "learning_rate": 1.2710983121350293e-06,
+      "loss": 0.4266,
+      "step": 1590
+    },
+    {
+      "epoch": 0.012799897600819194,
+      "grad_norm": 0.6685733935987979,
+      "learning_rate": 1.2790976721862253e-06,
+      "loss": 0.4148,
+      "step": 1600
+    },
+    {
+      "epoch": 0.012879896960824314,
+      "grad_norm": 0.829963069106683,
+      "learning_rate": 1.287097032237421e-06,
+      "loss": 0.438,
+      "step": 1610
+    },
+    {
+      "epoch": 0.012959896320829433,
+      "grad_norm": 0.8772001383565942,
+      "learning_rate": 1.295096392288617e-06,
+      "loss": 0.4167,
+      "step": 1620
+    },
+    {
+      "epoch": 0.013039895680834553,
+      "grad_norm": 0.7693529714105686,
+      "learning_rate": 1.303095752339813e-06,
+      "loss": 0.4465,
+      "step": 1630
+    },
+    {
+      "epoch": 0.013119895040839673,
+      "grad_norm": 0.6969819161826472,
+      "learning_rate": 1.3110951123910087e-06,
+      "loss": 0.4374,
+      "step": 1640
+    },
+    {
+      "epoch": 0.013199894400844793,
+      "grad_norm": 0.7245418409893126,
+      "learning_rate": 1.3190944724422048e-06,
+      "loss": 0.4375,
+      "step": 1650
+    },
+    {
+      "epoch": 0.013279893760849914,
+      "grad_norm": 0.6704658854506884,
+      "learning_rate": 1.3270938324934008e-06,
+      "loss": 0.4144,
+      "step": 1660
+    },
+    {
+      "epoch": 0.013359893120855034,
+      "grad_norm": 0.7596780468310279,
+      "learning_rate": 1.3350931925445965e-06,
+      "loss": 0.4142,
+      "step": 1670
+    },
+    {
+      "epoch": 0.013439892480860154,
+      "grad_norm": 0.799033496950235,
+      "learning_rate": 1.3430925525957924e-06,
+      "loss": 0.424,
+      "step": 1680
+    },
+    {
+      "epoch": 0.013519891840865272,
+      "grad_norm": 0.8360146268303155,
+      "learning_rate": 1.3510919126469885e-06,
+      "loss": 0.4104,
+      "step": 1690
+    },
+    {
+      "epoch": 0.013599891200870393,
+      "grad_norm": 0.7830381641790578,
+      "learning_rate": 1.3590912726981842e-06,
+      "loss": 0.4067,
+      "step": 1700
+    },
+    {
+      "epoch": 0.013679890560875513,
+      "grad_norm": 0.7376045815830132,
+      "learning_rate": 1.3670906327493801e-06,
+      "loss": 0.4232,
+      "step": 1710
+    },
+    {
+      "epoch": 0.013759889920880633,
+      "grad_norm": 0.7780257393234633,
+      "learning_rate": 1.3750899928005762e-06,
+      "loss": 0.4001,
+      "step": 1720
+    },
+    {
+      "epoch": 0.013839889280885753,
+      "grad_norm": 0.7400853428241427,
+      "learning_rate": 1.383089352851772e-06,
+      "loss": 0.4283,
+      "step": 1730
+    },
+    {
+      "epoch": 0.013919888640890873,
+      "grad_norm": 0.6301335389858812,
+      "learning_rate": 1.3910887129029679e-06,
+      "loss": 0.4315,
+      "step": 1740
+    },
+    {
+      "epoch": 0.013999888000895994,
+      "grad_norm": 0.6873058205506691,
+      "learning_rate": 1.3990880729541636e-06,
+      "loss": 0.4294,
+      "step": 1750
+    },
+    {
+      "epoch": 0.014079887360901112,
+      "grad_norm": 0.6118849450571252,
+      "learning_rate": 1.4070874330053597e-06,
+      "loss": 0.4116,
+      "step": 1760
+    },
+    {
+      "epoch": 0.014159886720906232,
+      "grad_norm": 0.8643963519063279,
+      "learning_rate": 1.4150867930565556e-06,
+      "loss": 0.4189,
+      "step": 1770
+    },
+    {
+      "epoch": 0.014239886080911352,
+      "grad_norm": 0.6986286668684888,
+      "learning_rate": 1.4230861531077513e-06,
+      "loss": 0.4393,
+      "step": 1780
+    },
+    {
+      "epoch": 0.014319885440916473,
+      "grad_norm": 0.7361554237470329,
+      "learning_rate": 1.4310855131589474e-06,
+      "loss": 0.4048,
+      "step": 1790
+    },
+    {
+      "epoch": 0.014399884800921593,
+      "grad_norm": 0.7526595512221772,
+      "learning_rate": 1.4390848732101434e-06,
+      "loss": 0.4434,
+      "step": 1800
+    },
+    {
+      "epoch": 0.014479884160926713,
+      "grad_norm": 0.6793121490590498,
+      "learning_rate": 1.447084233261339e-06,
+      "loss": 0.4313,
+      "step": 1810
+    },
+    {
+      "epoch": 0.014559883520931833,
+      "grad_norm": 0.7503593630371851,
+      "learning_rate": 1.4550835933125352e-06,
+      "loss": 0.4363,
+      "step": 1820
+    },
+    {
+      "epoch": 0.014639882880936952,
+      "grad_norm": 0.6631126747097913,
+      "learning_rate": 1.463082953363731e-06,
+      "loss": 0.4172,
+      "step": 1830
+    },
+    {
+      "epoch": 0.014719882240942072,
+      "grad_norm": 0.6201041671912539,
+      "learning_rate": 1.4710823134149268e-06,
+      "loss": 0.426,
+      "step": 1840
+    },
+    {
+      "epoch": 0.014799881600947192,
+      "grad_norm": 0.7986575840999489,
+      "learning_rate": 1.479081673466123e-06,
+      "loss": 0.4418,
+      "step": 1850
+    },
+    {
+      "epoch": 0.014879880960952312,
+      "grad_norm": 0.7485644191714067,
+      "learning_rate": 1.4870810335173188e-06,
+      "loss": 0.4315,
+      "step": 1860
+    },
+    {
+      "epoch": 0.014959880320957433,
+      "grad_norm": 0.767180980787683,
+      "learning_rate": 1.4950803935685146e-06,
+      "loss": 0.44,
+      "step": 1870
+    },
+    {
+      "epoch": 0.015039879680962553,
+      "grad_norm": 0.7085244935047633,
+      "learning_rate": 1.5030797536197107e-06,
+      "loss": 0.4197,
+      "step": 1880
+    },
+    {
+      "epoch": 0.015119879040967673,
+      "grad_norm": 0.9096558305501717,
+      "learning_rate": 1.5110791136709064e-06,
+      "loss": 0.4276,
+      "step": 1890
+    },
+    {
+      "epoch": 0.015199878400972791,
+      "grad_norm": 0.7782449144127891,
+      "learning_rate": 1.5190784737221023e-06,
+      "loss": 0.4433,
+      "step": 1900
+    },
+    {
+      "epoch": 0.015279877760977912,
+      "grad_norm": 0.6784288997728832,
+      "learning_rate": 1.5270778337732984e-06,
+      "loss": 0.408,
+      "step": 1910
+    },
+    {
+      "epoch": 0.015359877120983032,
+      "grad_norm": 0.7394160138728095,
+      "learning_rate": 1.5350771938244941e-06,
+      "loss": 0.427,
+      "step": 1920
+    },
+    {
+      "epoch": 0.015439876480988152,
+      "grad_norm": 0.7020184796096351,
+      "learning_rate": 1.54307655387569e-06,
+      "loss": 0.4585,
+      "step": 1930
+    },
+    {
+      "epoch": 0.015519875840993272,
+      "grad_norm": 0.6570216742745165,
+      "learning_rate": 1.551075913926886e-06,
+      "loss": 0.4203,
+      "step": 1940
+    },
+    {
+      "epoch": 0.015599875200998392,
+      "grad_norm": 0.6492915506893296,
+      "learning_rate": 1.5590752739780819e-06,
+      "loss": 0.4225,
+      "step": 1950
+    },
+    {
+      "epoch": 0.01567987456100351,
+      "grad_norm": 0.6404207960330748,
+      "learning_rate": 1.5670746340292778e-06,
+      "loss": 0.4155,
+      "step": 1960
+    },
+    {
+      "epoch": 0.01575987392100863,
+      "grad_norm": 0.7069937527425317,
+      "learning_rate": 1.5750739940804737e-06,
+      "loss": 0.4017,
+      "step": 1970
+    },
+    {
+      "epoch": 0.01583987328101375,
+      "grad_norm": 0.7497814910327999,
+      "learning_rate": 1.5830733541316694e-06,
+      "loss": 0.4336,
+      "step": 1980
+    },
+    {
+      "epoch": 0.01591987264101887,
+      "grad_norm": 0.997502334828043,
+      "learning_rate": 1.5910727141828655e-06,
+      "loss": 0.4252,
+      "step": 1990
+    },
+    {
+      "epoch": 0.01599987200102399,
+      "grad_norm": 0.7051737520195863,
+      "learning_rate": 1.5990720742340615e-06,
+      "loss": 0.4136,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 125001,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 115736344297472.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d0218b2de978c0fb669a44ee4979e8911e040543933e825b0f1ddf72ee6fdf
+size 7736

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/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 gc
+import json
+import numpy as np
+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, weights_only=False)
+
+        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 tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # 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}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] 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")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+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 = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * 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
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[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}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        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 to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=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
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    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.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    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")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+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,
+                                                          lazy_mode=True)
+
+    # 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")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_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 by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # 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)