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 +1,72 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "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": false,
+  "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"
+}

latest

@@ -0,0 +1 @@
+global_step388

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a719b3e2f3c68e7221a09f01920371af2b7d3e79ea9c30b2f937d9c8f6677723
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c5ad8bb82c7bf9612803c130df1890ed52814355fd2884d4f5f102ad2761ab
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4ce3bf0ba256c0b6f7b28db8e740d260c294f2882f3aeec247374d57bff706
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d126807064742956797e0c3d761c531ca1738c5240270a81cc7d47a0ed1408
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e8505511179d7dcf51d34cba5a40a74408090f8c9c128cf48e7389d2fc35623
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:454f0ca312975c08c0f97fcb10955f6cda20b6fe1af9c31e323e74420c0f39f2
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_parameters": 424960,
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0418786c564bb001fc5f4215375b1a99ed3ea3f30771057e1d8682214a0108f
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35deaabe10396919e53b2274736981b26bc690165c8839845f178b355a6a7588
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c5deee061a76a9e05b4634f5abad786b4042e744cc4c156a2ab76dc3c94fcac
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13579f7ca365ea6f9cef83929c34833cd97f9b5764a434989b4e3e2db87dce56
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073d0b1d7e2e3930e5c29fc418e6246462ab2a00396c3a86e1448d373503f1b2
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c60731015889939e665a308a0933ac6c327734a4699cf5615217db0cfaf03ca
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:416648e7a35618f28d73625751a8fc2ad066533414d19f6fc0c39932429023fc
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619b5c49446c94dca2b233ad17098e42f7d58a945c2eced1aa23e50469a75431
+size 16389

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a296aab115706767317925889fb703144b496319e0500fded3a8c8d0f7b6afc5
+size 1465

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 +1,2750 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 388,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005154639175257732,
+      "grad_norm": 16.203728734181727,
+      "learning_rate": 0.0,
+      "loss": 0.782,
+      "step": 1
+    },
+    {
+      "epoch": 0.010309278350515464,
+      "grad_norm": 17.966080542459263,
+      "learning_rate": 1.6949152542372883e-07,
+      "loss": 0.8806,
+      "step": 2
+    },
+    {
+      "epoch": 0.015463917525773196,
+      "grad_norm": 19.39755361913842,
+      "learning_rate": 3.3898305084745766e-07,
+      "loss": 0.9713,
+      "step": 3
+    },
+    {
+      "epoch": 0.020618556701030927,
+      "grad_norm": 18.521681485723096,
+      "learning_rate": 5.084745762711865e-07,
+      "loss": 0.7594,
+      "step": 4
+    },
+    {
+      "epoch": 0.02577319587628866,
+      "grad_norm": 16.960097281692487,
+      "learning_rate": 6.779661016949153e-07,
+      "loss": 1.0095,
+      "step": 5
+    },
+    {
+      "epoch": 0.030927835051546393,
+      "grad_norm": 17.9303091015193,
+      "learning_rate": 8.474576271186441e-07,
+      "loss": 1.0024,
+      "step": 6
+    },
+    {
+      "epoch": 0.03608247422680412,
+      "grad_norm": 16.393493317929863,
+      "learning_rate": 1.016949152542373e-06,
+      "loss": 0.7936,
+      "step": 7
+    },
+    {
+      "epoch": 0.041237113402061855,
+      "grad_norm": 16.350575208232332,
+      "learning_rate": 1.186440677966102e-06,
+      "loss": 0.6727,
+      "step": 8
+    },
+    {
+      "epoch": 0.04639175257731959,
+      "grad_norm": 13.392733244736176,
+      "learning_rate": 1.3559322033898307e-06,
+      "loss": 0.6366,
+      "step": 9
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 13.99345418325563,
+      "learning_rate": 1.5254237288135596e-06,
+      "loss": 0.8352,
+      "step": 10
+    },
+    {
+      "epoch": 0.05670103092783505,
+      "grad_norm": 16.574632940102198,
+      "learning_rate": 1.6949152542372882e-06,
+      "loss": 0.8211,
+      "step": 11
+    },
+    {
+      "epoch": 0.061855670103092786,
+      "grad_norm": 7.432819145467484,
+      "learning_rate": 1.8644067796610171e-06,
+      "loss": 0.4671,
+      "step": 12
+    },
+    {
+      "epoch": 0.06701030927835051,
+      "grad_norm": 7.368792116734323,
+      "learning_rate": 2.033898305084746e-06,
+      "loss": 0.4617,
+      "step": 13
+    },
+    {
+      "epoch": 0.07216494845360824,
+      "grad_norm": 5.189955956808789,
+      "learning_rate": 2.203389830508475e-06,
+      "loss": 0.4118,
+      "step": 14
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 6.110418564319445,
+      "learning_rate": 2.372881355932204e-06,
+      "loss": 0.4772,
+      "step": 15
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 2.524741574511695,
+      "learning_rate": 2.5423728813559323e-06,
+      "loss": 0.1693,
+      "step": 16
+    },
+    {
+      "epoch": 0.08762886597938144,
+      "grad_norm": 4.093704704249702,
+      "learning_rate": 2.7118644067796613e-06,
+      "loss": 0.5946,
+      "step": 17
+    },
+    {
+      "epoch": 0.09278350515463918,
+      "grad_norm": 2.792475441128467,
+      "learning_rate": 2.8813559322033903e-06,
+      "loss": 0.3907,
+      "step": 18
+    },
+    {
+      "epoch": 0.0979381443298969,
+      "grad_norm": 2.8142697054484422,
+      "learning_rate": 3.0508474576271192e-06,
+      "loss": 0.4128,
+      "step": 19
+    },
+    {
+      "epoch": 0.10309278350515463,
+      "grad_norm": 3.0557753995059835,
+      "learning_rate": 3.2203389830508473e-06,
+      "loss": 0.4128,
+      "step": 20
+    },
+    {
+      "epoch": 0.10824742268041238,
+      "grad_norm": 2.407462983991879,
+      "learning_rate": 3.3898305084745763e-06,
+      "loss": 0.2454,
+      "step": 21
+    },
+    {
+      "epoch": 0.1134020618556701,
+      "grad_norm": 4.175164045570657,
+      "learning_rate": 3.5593220338983053e-06,
+      "loss": 0.5676,
+      "step": 22
+    },
+    {
+      "epoch": 0.11855670103092783,
+      "grad_norm": 3.2745984458679542,
+      "learning_rate": 3.7288135593220342e-06,
+      "loss": 0.3725,
+      "step": 23
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 2.630482014005189,
+      "learning_rate": 3.898305084745763e-06,
+      "loss": 0.284,
+      "step": 24
+    },
+    {
+      "epoch": 0.12886597938144329,
+      "grad_norm": 2.5818523655885657,
+      "learning_rate": 4.067796610169492e-06,
+      "loss": 0.3914,
+      "step": 25
+    },
+    {
+      "epoch": 0.13402061855670103,
+      "grad_norm": 2.1862545024847733,
+      "learning_rate": 4.23728813559322e-06,
+      "loss": 0.3245,
+      "step": 26
+    },
+    {
+      "epoch": 0.13917525773195877,
+      "grad_norm": 1.8029553321125102,
+      "learning_rate": 4.40677966101695e-06,
+      "loss": 0.1906,
+      "step": 27
+    },
+    {
+      "epoch": 0.14432989690721648,
+      "grad_norm": 2.1274587742776228,
+      "learning_rate": 4.576271186440678e-06,
+      "loss": 0.3129,
+      "step": 28
+    },
+    {
+      "epoch": 0.14948453608247422,
+      "grad_norm": 2.0553069128433985,
+      "learning_rate": 4.745762711864408e-06,
+      "loss": 0.362,
+      "step": 29
+    },
+    {
+      "epoch": 0.15463917525773196,
+      "grad_norm": 2.2636243270640812,
+      "learning_rate": 4.915254237288136e-06,
+      "loss": 0.3487,
+      "step": 30
+    },
+    {
+      "epoch": 0.15979381443298968,
+      "grad_norm": 2.0627428648390023,
+      "learning_rate": 5.084745762711865e-06,
+      "loss": 0.3017,
+      "step": 31
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 1.707507687529141,
+      "learning_rate": 5.254237288135594e-06,
+      "loss": 0.2379,
+      "step": 32
+    },
+    {
+      "epoch": 0.17010309278350516,
+      "grad_norm": 1.6433474151177994,
+      "learning_rate": 5.423728813559323e-06,
+      "loss": 0.2785,
+      "step": 33
+    },
+    {
+      "epoch": 0.17525773195876287,
+      "grad_norm": 1.8049400111968015,
+      "learning_rate": 5.593220338983051e-06,
+      "loss": 0.2046,
+      "step": 34
+    },
+    {
+      "epoch": 0.18041237113402062,
+      "grad_norm": 1.956624509674235,
+      "learning_rate": 5.7627118644067805e-06,
+      "loss": 0.2924,
+      "step": 35
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 2.043442546886233,
+      "learning_rate": 5.932203389830509e-06,
+      "loss": 0.2517,
+      "step": 36
+    },
+    {
+      "epoch": 0.19072164948453607,
+      "grad_norm": 1.7809412898084382,
+      "learning_rate": 6.1016949152542385e-06,
+      "loss": 0.214,
+      "step": 37
+    },
+    {
+      "epoch": 0.1958762886597938,
+      "grad_norm": 1.0871959933984234,
+      "learning_rate": 6.271186440677966e-06,
+      "loss": 0.0794,
+      "step": 38
+    },
+    {
+      "epoch": 0.20103092783505155,
+      "grad_norm": 1.6627701820242757,
+      "learning_rate": 6.440677966101695e-06,
+      "loss": 0.1529,
+      "step": 39
+    },
+    {
+      "epoch": 0.20618556701030927,
+      "grad_norm": 2.233281327693517,
+      "learning_rate": 6.610169491525424e-06,
+      "loss": 0.3918,
+      "step": 40
+    },
+    {
+      "epoch": 0.211340206185567,
+      "grad_norm": 2.4810527246233143,
+      "learning_rate": 6.779661016949153e-06,
+      "loss": 0.3276,
+      "step": 41
+    },
+    {
+      "epoch": 0.21649484536082475,
+      "grad_norm": 2.138313718866784,
+      "learning_rate": 6.949152542372882e-06,
+      "loss": 0.1874,
+      "step": 42
+    },
+    {
+      "epoch": 0.22164948453608246,
+      "grad_norm": 2.3207138440634445,
+      "learning_rate": 7.1186440677966106e-06,
+      "loss": 0.143,
+      "step": 43
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 1.806845922939825,
+      "learning_rate": 7.288135593220339e-06,
+      "loss": 0.2639,
+      "step": 44
+    },
+    {
+      "epoch": 0.23195876288659795,
+      "grad_norm": 1.6856465858879643,
+      "learning_rate": 7.4576271186440685e-06,
+      "loss": 0.1803,
+      "step": 45
+    },
+    {
+      "epoch": 0.23711340206185566,
+      "grad_norm": 1.8626644402225192,
+      "learning_rate": 7.627118644067797e-06,
+      "loss": 0.2046,
+      "step": 46
+    },
+    {
+      "epoch": 0.2422680412371134,
+      "grad_norm": 1.7027465927641543,
+      "learning_rate": 7.796610169491526e-06,
+      "loss": 0.124,
+      "step": 47
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 1.9041870166779817,
+      "learning_rate": 7.966101694915255e-06,
+      "loss": 0.1982,
+      "step": 48
+    },
+    {
+      "epoch": 0.25257731958762886,
+      "grad_norm": 1.770069442877448,
+      "learning_rate": 8.135593220338983e-06,
+      "loss": 0.2813,
+      "step": 49
+    },
+    {
+      "epoch": 0.25773195876288657,
+      "grad_norm": 1.953365961357983,
+      "learning_rate": 8.305084745762712e-06,
+      "loss": 0.2251,
+      "step": 50
+    },
+    {
+      "epoch": 0.26288659793814434,
+      "grad_norm": 2.002309230380239,
+      "learning_rate": 8.47457627118644e-06,
+      "loss": 0.2785,
+      "step": 51
+    },
+    {
+      "epoch": 0.26804123711340205,
+      "grad_norm": 1.5522236927921595,
+      "learning_rate": 8.64406779661017e-06,
+      "loss": 0.2388,
+      "step": 52
+    },
+    {
+      "epoch": 0.27319587628865977,
+      "grad_norm": 1.4065957481275269,
+      "learning_rate": 8.8135593220339e-06,
+      "loss": 0.1592,
+      "step": 53
+    },
+    {
+      "epoch": 0.27835051546391754,
+      "grad_norm": 1.344843484282986,
+      "learning_rate": 8.983050847457628e-06,
+      "loss": 0.184,
+      "step": 54
+    },
+    {
+      "epoch": 0.28350515463917525,
+      "grad_norm": 1.8809824575076326,
+      "learning_rate": 9.152542372881356e-06,
+      "loss": 0.1559,
+      "step": 55
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 1.554740329023379,
+      "learning_rate": 9.322033898305085e-06,
+      "loss": 0.1945,
+      "step": 56
+    },
+    {
+      "epoch": 0.29381443298969073,
+      "grad_norm": 1.7706197688983198,
+      "learning_rate": 9.491525423728815e-06,
+      "loss": 0.2799,
+      "step": 57
+    },
+    {
+      "epoch": 0.29896907216494845,
+      "grad_norm": 1.339143828253002,
+      "learning_rate": 9.661016949152544e-06,
+      "loss": 0.1094,
+      "step": 58
+    },
+    {
+      "epoch": 0.30412371134020616,
+      "grad_norm": 2.1220725285103086,
+      "learning_rate": 9.830508474576272e-06,
+      "loss": 0.3211,
+      "step": 59
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 1.3971936674913341,
+      "learning_rate": 1e-05,
+      "loss": 0.2081,
+      "step": 60
+    },
+    {
+      "epoch": 0.31443298969072164,
+      "grad_norm": 1.8165010693502677,
+      "learning_rate": 9.999909794073715e-06,
+      "loss": 0.191,
+      "step": 61
+    },
+    {
+      "epoch": 0.31958762886597936,
+      "grad_norm": 1.8206712917879821,
+      "learning_rate": 9.999639179549699e-06,
+      "loss": 0.1817,
+      "step": 62
+    },
+    {
+      "epoch": 0.3247422680412371,
+      "grad_norm": 2.1904370888969704,
+      "learning_rate": 9.999188166192368e-06,
+      "loss": 0.1933,
+      "step": 63
+    },
+    {
+      "epoch": 0.32989690721649484,
+      "grad_norm": 1.356123942482486,
+      "learning_rate": 9.998556770275351e-06,
+      "loss": 0.1529,
+      "step": 64
+    },
+    {
+      "epoch": 0.33505154639175255,
+      "grad_norm": 1.4167068373050817,
+      "learning_rate": 9.997745014580912e-06,
+      "loss": 0.2182,
+      "step": 65
+    },
+    {
+      "epoch": 0.3402061855670103,
+      "grad_norm": 1.2778114297184384,
+      "learning_rate": 9.996752928399121e-06,
+      "loss": 0.1231,
+      "step": 66
+    },
+    {
+      "epoch": 0.34536082474226804,
+      "grad_norm": 1.4693549048926278,
+      "learning_rate": 9.995580547526798e-06,
+      "loss": 0.2222,
+      "step": 67
+    },
+    {
+      "epoch": 0.35051546391752575,
+      "grad_norm": 1.4349642188073422,
+      "learning_rate": 9.994227914266222e-06,
+      "loss": 0.1934,
+      "step": 68
+    },
+    {
+      "epoch": 0.3556701030927835,
+      "grad_norm": 1.3639498444936125,
+      "learning_rate": 9.992695077423609e-06,
+      "loss": 0.1707,
+      "step": 69
+    },
+    {
+      "epoch": 0.36082474226804123,
+      "grad_norm": 1.3943030751682663,
+      "learning_rate": 9.990982092307347e-06,
+      "loss": 0.1716,
+      "step": 70
+    },
+    {
+      "epoch": 0.36597938144329895,
+      "grad_norm": 1.4616151628165952,
+      "learning_rate": 9.989089020725999e-06,
+      "loss": 0.2363,
+      "step": 71
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 1.7297954033170302,
+      "learning_rate": 9.987015930986074e-06,
+      "loss": 0.0612,
+      "step": 72
+    },
+    {
+      "epoch": 0.37628865979381443,
+      "grad_norm": 1.4130551566794556,
+      "learning_rate": 9.984762897889568e-06,
+      "loss": 0.2438,
+      "step": 73
+    },
+    {
+      "epoch": 0.38144329896907214,
+      "grad_norm": 1.4316589582684316,
+      "learning_rate": 9.98233000273125e-06,
+      "loss": 0.2529,
+      "step": 74
+    },
+    {
+      "epoch": 0.3865979381443299,
+      "grad_norm": 1.4921368045815033,
+      "learning_rate": 9.97971733329575e-06,
+      "loss": 0.2033,
+      "step": 75
+    },
+    {
+      "epoch": 0.3917525773195876,
+      "grad_norm": 1.6884913833837993,
+      "learning_rate": 9.97692498385437e-06,
+      "loss": 0.3251,
+      "step": 76
+    },
+    {
+      "epoch": 0.39690721649484534,
+      "grad_norm": 1.2618275142031115,
+      "learning_rate": 9.973953055161702e-06,
+      "loss": 0.2173,
+      "step": 77
+    },
+    {
+      "epoch": 0.4020618556701031,
+      "grad_norm": 1.2058891275808017,
+      "learning_rate": 9.970801654451974e-06,
+      "loss": 0.1337,
+      "step": 78
+    },
+    {
+      "epoch": 0.4072164948453608,
+      "grad_norm": 1.3014010097389481,
+      "learning_rate": 9.967470895435197e-06,
+      "loss": 0.2217,
+      "step": 79
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 1.0907558669955588,
+      "learning_rate": 9.963960898293049e-06,
+      "loss": 0.1166,
+      "step": 80
+    },
+    {
+      "epoch": 0.4175257731958763,
+      "grad_norm": 1.3508925279475854,
+      "learning_rate": 9.96027178967455e-06,
+      "loss": 0.2185,
+      "step": 81
+    },
+    {
+      "epoch": 0.422680412371134,
+      "grad_norm": 1.8405638710013943,
+      "learning_rate": 9.956403702691482e-06,
+      "loss": 0.2981,
+      "step": 82
+    },
+    {
+      "epoch": 0.42783505154639173,
+      "grad_norm": 0.9981831988732881,
+      "learning_rate": 9.952356776913594e-06,
+      "loss": 0.1471,
+      "step": 83
+    },
+    {
+      "epoch": 0.4329896907216495,
+      "grad_norm": 1.5438578399853147,
+      "learning_rate": 9.948131158363564e-06,
+      "loss": 0.2219,
+      "step": 84
+    },
+    {
+      "epoch": 0.4381443298969072,
+      "grad_norm": 1.373967099765683,
+      "learning_rate": 9.943726999511721e-06,
+      "loss": 0.2625,
+      "step": 85
+    },
+    {
+      "epoch": 0.44329896907216493,
+      "grad_norm": 1.5045665327970632,
+      "learning_rate": 9.939144459270557e-06,
+      "loss": 0.2378,
+      "step": 86
+    },
+    {
+      "epoch": 0.4484536082474227,
+      "grad_norm": 1.2348801218707532,
+      "learning_rate": 9.934383702988992e-06,
+      "loss": 0.1299,
+      "step": 87
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 1.3457854200982862,
+      "learning_rate": 9.929444902446392e-06,
+      "loss": 0.2193,
+      "step": 88
+    },
+    {
+      "epoch": 0.4587628865979381,
+      "grad_norm": 1.5974941630503592,
+      "learning_rate": 9.924328235846393e-06,
+      "loss": 0.3447,
+      "step": 89
+    },
+    {
+      "epoch": 0.4639175257731959,
+      "grad_norm": 1.7921462524347982,
+      "learning_rate": 9.919033887810451e-06,
+      "loss": 0.3081,
+      "step": 90
+    },
+    {
+      "epoch": 0.4690721649484536,
+      "grad_norm": 1.0544333428105994,
+      "learning_rate": 9.913562049371196e-06,
+      "loss": 0.1723,
+      "step": 91
+    },
+    {
+      "epoch": 0.4742268041237113,
+      "grad_norm": 1.173180659355975,
+      "learning_rate": 9.90791291796553e-06,
+      "loss": 0.1816,
+      "step": 92
+    },
+    {
+      "epoch": 0.4793814432989691,
+      "grad_norm": 1.2343501847799747,
+      "learning_rate": 9.902086697427504e-06,
+      "loss": 0.2048,
+      "step": 93
+    },
+    {
+      "epoch": 0.4845360824742268,
+      "grad_norm": 1.4166315003510848,
+      "learning_rate": 9.896083597980968e-06,
+      "loss": 0.1611,
+      "step": 94
+    },
+    {
+      "epoch": 0.4896907216494845,
+      "grad_norm": 0.9316258247144923,
+      "learning_rate": 9.88990383623198e-06,
+      "loss": 0.1307,
+      "step": 95
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 1.1284196528102999,
+      "learning_rate": 9.883547635160991e-06,
+      "loss": 0.1816,
+      "step": 96
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.9136263992805103,
+      "learning_rate": 9.877015224114806e-06,
+      "loss": 0.1173,
+      "step": 97
+    },
+    {
+      "epoch": 0.5051546391752577,
+      "grad_norm": 1.5233730471599805,
+      "learning_rate": 9.870306838798299e-06,
+      "loss": 0.2239,
+      "step": 98
+    },
+    {
+      "epoch": 0.5103092783505154,
+      "grad_norm": 1.4031394060036828,
+      "learning_rate": 9.863422721265913e-06,
+      "loss": 0.2398,
+      "step": 99
+    },
+    {
+      "epoch": 0.5154639175257731,
+      "grad_norm": 1.12765997685746,
+      "learning_rate": 9.856363119912931e-06,
+      "loss": 0.1318,
+      "step": 100
+    },
+    {
+      "epoch": 0.520618556701031,
+      "grad_norm": 0.8420145818838017,
+      "learning_rate": 9.849128289466503e-06,
+      "loss": 0.1246,
+      "step": 101
+    },
+    {
+      "epoch": 0.5257731958762887,
+      "grad_norm": 0.946095131905409,
+      "learning_rate": 9.841718490976461e-06,
+      "loss": 0.1241,
+      "step": 102
+    },
+    {
+      "epoch": 0.5309278350515464,
+      "grad_norm": 0.9796883673872017,
+      "learning_rate": 9.8341339918059e-06,
+      "loss": 0.0955,
+      "step": 103
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 1.1930460993410585,
+      "learning_rate": 9.826375065621533e-06,
+      "loss": 0.1646,
+      "step": 104
+    },
+    {
+      "epoch": 0.5412371134020618,
+      "grad_norm": 1.27651192729961,
+      "learning_rate": 9.818441992383802e-06,
+      "loss": 0.1566,
+      "step": 105
+    },
+    {
+      "epoch": 0.5463917525773195,
+      "grad_norm": 1.1315939745886057,
+      "learning_rate": 9.810335058336801e-06,
+      "loss": 0.1786,
+      "step": 106
+    },
+    {
+      "epoch": 0.5515463917525774,
+      "grad_norm": 0.9355015058700618,
+      "learning_rate": 9.802054555997927e-06,
+      "loss": 0.0945,
+      "step": 107
+    },
+    {
+      "epoch": 0.5567010309278351,
+      "grad_norm": 1.7639349345635655,
+      "learning_rate": 9.79360078414733e-06,
+      "loss": 0.254,
+      "step": 108
+    },
+    {
+      "epoch": 0.5618556701030928,
+      "grad_norm": 1.3663266258683646,
+      "learning_rate": 9.784974047817142e-06,
+      "loss": 0.1953,
+      "step": 109
+    },
+    {
+      "epoch": 0.5670103092783505,
+      "grad_norm": 1.441702754636908,
+      "learning_rate": 9.776174658280458e-06,
+      "loss": 0.1841,
+      "step": 110
+    },
+    {
+      "epoch": 0.5721649484536082,
+      "grad_norm": 1.1499799893613811,
+      "learning_rate": 9.767202933040111e-06,
+      "loss": 0.1997,
+      "step": 111
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 1.2076330399094353,
+      "learning_rate": 9.758059195817216e-06,
+      "loss": 0.1768,
+      "step": 112
+    },
+    {
+      "epoch": 0.5824742268041238,
+      "grad_norm": 0.878277090541755,
+      "learning_rate": 9.748743776539489e-06,
+      "loss": 0.1173,
+      "step": 113
+    },
+    {
+      "epoch": 0.5876288659793815,
+      "grad_norm": 1.0228670375234183,
+      "learning_rate": 9.739257011329336e-06,
+      "loss": 0.1361,
+      "step": 114
+    },
+    {
+      "epoch": 0.5927835051546392,
+      "grad_norm": 1.4761049929099612,
+      "learning_rate": 9.729599242491738e-06,
+      "loss": 0.2792,
+      "step": 115
+    },
+    {
+      "epoch": 0.5979381443298969,
+      "grad_norm": 1.0296746075367031,
+      "learning_rate": 9.719770818501885e-06,
+      "loss": 0.1,
+      "step": 116
+    },
+    {
+      "epoch": 0.6030927835051546,
+      "grad_norm": 0.9546648084132865,
+      "learning_rate": 9.709772093992619e-06,
+      "loss": 0.1072,
+      "step": 117
+    },
+    {
+      "epoch": 0.6082474226804123,
+      "grad_norm": 0.9359977344927911,
+      "learning_rate": 9.699603429741615e-06,
+      "loss": 0.1171,
+      "step": 118
+    },
+    {
+      "epoch": 0.6134020618556701,
+      "grad_norm": 1.2912642891989952,
+      "learning_rate": 9.689265192658387e-06,
+      "loss": 0.1783,
+      "step": 119
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 1.1169115856391039,
+      "learning_rate": 9.67875775577104e-06,
+      "loss": 0.2051,
+      "step": 120
+    },
+    {
+      "epoch": 0.6237113402061856,
+      "grad_norm": 1.4787464277701932,
+      "learning_rate": 9.668081498212799e-06,
+      "loss": 0.2377,
+      "step": 121
+    },
+    {
+      "epoch": 0.6288659793814433,
+      "grad_norm": 0.9403827546416947,
+      "learning_rate": 9.657236805208347e-06,
+      "loss": 0.1219,
+      "step": 122
+    },
+    {
+      "epoch": 0.634020618556701,
+      "grad_norm": 0.7358413148522787,
+      "learning_rate": 9.646224068059917e-06,
+      "loss": 0.0895,
+      "step": 123
+    },
+    {
+      "epoch": 0.6391752577319587,
+      "grad_norm": 1.1530465641868872,
+      "learning_rate": 9.63504368413317e-06,
+      "loss": 0.2149,
+      "step": 124
+    },
+    {
+      "epoch": 0.6443298969072165,
+      "grad_norm": 1.4217244985998034,
+      "learning_rate": 9.62369605684286e-06,
+      "loss": 0.197,
+      "step": 125
+    },
+    {
+      "epoch": 0.6494845360824743,
+      "grad_norm": 1.910749720256578,
+      "learning_rate": 9.612181595638279e-06,
+      "loss": 0.2508,
+      "step": 126
+    },
+    {
+      "epoch": 0.654639175257732,
+      "grad_norm": 1.2757659427730983,
+      "learning_rate": 9.600500715988486e-06,
+      "loss": 0.2809,
+      "step": 127
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 1.0891754027329807,
+      "learning_rate": 9.588653839367304e-06,
+      "loss": 0.165,
+      "step": 128
+    },
+    {
+      "epoch": 0.6649484536082474,
+      "grad_norm": 1.293429113847632,
+      "learning_rate": 9.576641393238129e-06,
+      "loss": 0.0855,
+      "step": 129
+    },
+    {
+      "epoch": 0.6701030927835051,
+      "grad_norm": 1.4599213966596118,
+      "learning_rate": 9.564463811038489e-06,
+      "loss": 0.2503,
+      "step": 130
+    },
+    {
+      "epoch": 0.6752577319587629,
+      "grad_norm": 1.3648021125385577,
+      "learning_rate": 9.55212153216442e-06,
+      "loss": 0.1794,
+      "step": 131
+    },
+    {
+      "epoch": 0.6804123711340206,
+      "grad_norm": 0.9809648930976671,
+      "learning_rate": 9.5396150019546e-06,
+      "loss": 0.0749,
+      "step": 132
+    },
+    {
+      "epoch": 0.6855670103092784,
+      "grad_norm": 1.2479101653995877,
+      "learning_rate": 9.526944671674287e-06,
+      "loss": 0.1705,
+      "step": 133
+    },
+    {
+      "epoch": 0.6907216494845361,
+      "grad_norm": 1.180767703263976,
+      "learning_rate": 9.514110998499032e-06,
+      "loss": 0.2419,
+      "step": 134
+    },
+    {
+      "epoch": 0.6958762886597938,
+      "grad_norm": 0.9973862175809532,
+      "learning_rate": 9.501114445498183e-06,
+      "loss": 0.1545,
+      "step": 135
+    },
+    {
+      "epoch": 0.7010309278350515,
+      "grad_norm": 0.9580969711134073,
+      "learning_rate": 9.487955481618184e-06,
+      "loss": 0.1563,
+      "step": 136
+    },
+    {
+      "epoch": 0.7061855670103093,
+      "grad_norm": 1.0576903096823542,
+      "learning_rate": 9.474634581665645e-06,
+      "loss": 0.128,
+      "step": 137
+    },
+    {
+      "epoch": 0.711340206185567,
+      "grad_norm": 1.1608177511918483,
+      "learning_rate": 9.461152226290212e-06,
+      "loss": 0.2324,
+      "step": 138
+    },
+    {
+      "epoch": 0.7164948453608248,
+      "grad_norm": 0.7247855062304921,
+      "learning_rate": 9.44750890196723e-06,
+      "loss": 0.0696,
+      "step": 139
+    },
+    {
+      "epoch": 0.7216494845360825,
+      "grad_norm": 1.294941334572682,
+      "learning_rate": 9.43370510098018e-06,
+      "loss": 0.2068,
+      "step": 140
+    },
+    {
+      "epoch": 0.7268041237113402,
+      "grad_norm": 1.5307061314891508,
+      "learning_rate": 9.419741321402923e-06,
+      "loss": 0.134,
+      "step": 141
+    },
+    {
+      "epoch": 0.7319587628865979,
+      "grad_norm": 1.724248389396898,
+      "learning_rate": 9.405618067081729e-06,
+      "loss": 0.3587,
+      "step": 142
+    },
+    {
+      "epoch": 0.7371134020618557,
+      "grad_norm": 0.7880104208217124,
+      "learning_rate": 9.391335847617093e-06,
+      "loss": 0.1081,
+      "step": 143
+    },
+    {
+      "epoch": 0.7422680412371134,
+      "grad_norm": 1.176218642717777,
+      "learning_rate": 9.37689517834535e-06,
+      "loss": 0.2552,
+      "step": 144
+    },
+    {
+      "epoch": 0.7474226804123711,
+      "grad_norm": 0.9007810641742303,
+      "learning_rate": 9.362296580320078e-06,
+      "loss": 0.1411,
+      "step": 145
+    },
+    {
+      "epoch": 0.7525773195876289,
+      "grad_norm": 1.0987174332049452,
+      "learning_rate": 9.347540580293301e-06,
+      "loss": 0.1984,
+      "step": 146
+    },
+    {
+      "epoch": 0.7577319587628866,
+      "grad_norm": 0.9593956667801066,
+      "learning_rate": 9.332627710696477e-06,
+      "loss": 0.1403,
+      "step": 147
+    },
+    {
+      "epoch": 0.7628865979381443,
+      "grad_norm": 1.5203788468340629,
+      "learning_rate": 9.317558509621297e-06,
+      "loss": 0.3035,
+      "step": 148
+    },
+    {
+      "epoch": 0.7680412371134021,
+      "grad_norm": 0.9687515693670804,
+      "learning_rate": 9.302333520800253e-06,
+      "loss": 0.1366,
+      "step": 149
+    },
+    {
+      "epoch": 0.7731958762886598,
+      "grad_norm": 0.7832678330612435,
+      "learning_rate": 9.286953293587035e-06,
+      "loss": 0.11,
+      "step": 150
+    },
+    {
+      "epoch": 0.7783505154639175,
+      "grad_norm": 0.9289801978987015,
+      "learning_rate": 9.271418382936697e-06,
+      "loss": 0.0988,
+      "step": 151
+    },
+    {
+      "epoch": 0.7835051546391752,
+      "grad_norm": 1.1356540696916577,
+      "learning_rate": 9.255729349385645e-06,
+      "loss": 0.1375,
+      "step": 152
+    },
+    {
+      "epoch": 0.788659793814433,
+      "grad_norm": 1.3495379294095782,
+      "learning_rate": 9.239886759031399e-06,
+      "loss": 0.3033,
+      "step": 153
+    },
+    {
+      "epoch": 0.7938144329896907,
+      "grad_norm": 1.2612818337900333,
+      "learning_rate": 9.223891183512174e-06,
+      "loss": 0.1364,
+      "step": 154
+    },
+    {
+      "epoch": 0.7989690721649485,
+      "grad_norm": 1.1325852394462053,
+      "learning_rate": 9.207743199986252e-06,
+      "loss": 0.1559,
+      "step": 155
+    },
+    {
+      "epoch": 0.8041237113402062,
+      "grad_norm": 0.6629329908683664,
+      "learning_rate": 9.191443391111157e-06,
+      "loss": 0.0678,
+      "step": 156
+    },
+    {
+      "epoch": 0.8092783505154639,
+      "grad_norm": 1.184280051526035,
+      "learning_rate": 9.174992345022636e-06,
+      "loss": 0.1762,
+      "step": 157
+    },
+    {
+      "epoch": 0.8144329896907216,
+      "grad_norm": 1.4363833078261825,
+      "learning_rate": 9.158390655313422e-06,
+      "loss": 0.2509,
+      "step": 158
+    },
+    {
+      "epoch": 0.8195876288659794,
+      "grad_norm": 1.4851296678460735,
+      "learning_rate": 9.141638921011842e-06,
+      "loss": 0.3053,
+      "step": 159
+    },
+    {
+      "epoch": 0.8247422680412371,
+      "grad_norm": 0.9939630731717258,
+      "learning_rate": 9.124737746560175e-06,
+      "loss": 0.0952,
+      "step": 160
+    },
+    {
+      "epoch": 0.8298969072164949,
+      "grad_norm": 1.2169101845107388,
+      "learning_rate": 9.107687741792863e-06,
+      "loss": 0.1494,
+      "step": 161
+    },
+    {
+      "epoch": 0.8350515463917526,
+      "grad_norm": 1.3295674637794006,
+      "learning_rate": 9.090489521914492e-06,
+      "loss": 0.2761,
+      "step": 162
+    },
+    {
+      "epoch": 0.8402061855670103,
+      "grad_norm": 1.2793707854001373,
+      "learning_rate": 9.073143707477607e-06,
+      "loss": 0.1433,
+      "step": 163
+    },
+    {
+      "epoch": 0.845360824742268,
+      "grad_norm": 1.2039862398086603,
+      "learning_rate": 9.055650924360308e-06,
+      "loss": 0.2154,
+      "step": 164
+    },
+    {
+      "epoch": 0.8505154639175257,
+      "grad_norm": 1.1250244597985437,
+      "learning_rate": 9.038011803743679e-06,
+      "loss": 0.1817,
+      "step": 165
+    },
+    {
+      "epoch": 0.8556701030927835,
+      "grad_norm": 1.1063531458560925,
+      "learning_rate": 9.020226982089005e-06,
+      "loss": 0.1564,
+      "step": 166
+    },
+    {
+      "epoch": 0.8608247422680413,
+      "grad_norm": 1.1306904530717008,
+      "learning_rate": 9.002297101114813e-06,
+      "loss": 0.1349,
+      "step": 167
+    },
+    {
+      "epoch": 0.865979381443299,
+      "grad_norm": 1.0467505323127504,
+      "learning_rate": 8.984222807773707e-06,
+      "loss": 0.1813,
+      "step": 168
+    },
+    {
+      "epoch": 0.8711340206185567,
+      "grad_norm": 1.715578103301857,
+      "learning_rate": 8.966004754229037e-06,
+      "loss": 0.3016,
+      "step": 169
+    },
+    {
+      "epoch": 0.8762886597938144,
+      "grad_norm": 0.9646361196653148,
+      "learning_rate": 8.947643597831365e-06,
+      "loss": 0.0727,
+      "step": 170
+    },
+    {
+      "epoch": 0.8814432989690721,
+      "grad_norm": 0.9218462690369367,
+      "learning_rate": 8.929140001094734e-06,
+      "loss": 0.1584,
+      "step": 171
+    },
+    {
+      "epoch": 0.8865979381443299,
+      "grad_norm": 0.9892292920559456,
+      "learning_rate": 8.910494631672783e-06,
+      "loss": 0.1449,
+      "step": 172
+    },
+    {
+      "epoch": 0.8917525773195877,
+      "grad_norm": 1.0579410641324796,
+      "learning_rate": 8.891708162334635e-06,
+      "loss": 0.156,
+      "step": 173
+    },
+    {
+      "epoch": 0.8969072164948454,
+      "grad_norm": 0.7647207044009656,
+      "learning_rate": 8.87278127094064e-06,
+      "loss": 0.1107,
+      "step": 174
+    },
+    {
+      "epoch": 0.9020618556701031,
+      "grad_norm": 1.1371579318359795,
+      "learning_rate": 8.853714640417906e-06,
+      "loss": 0.1844,
+      "step": 175
+    },
+    {
+      "epoch": 0.9072164948453608,
+      "grad_norm": 0.7724480629708496,
+      "learning_rate": 8.834508958735656e-06,
+      "loss": 0.0826,
+      "step": 176
+    },
+    {
+      "epoch": 0.9123711340206185,
+      "grad_norm": 1.0272763923631063,
+      "learning_rate": 8.815164918880418e-06,
+      "loss": 0.1678,
+      "step": 177
+    },
+    {
+      "epoch": 0.9175257731958762,
+      "grad_norm": 1.2865546631779095,
+      "learning_rate": 8.795683218831002e-06,
+      "loss": 0.2714,
+      "step": 178
+    },
+    {
+      "epoch": 0.9226804123711341,
+      "grad_norm": 1.8028031060416778,
+      "learning_rate": 8.776064561533329e-06,
+      "loss": 0.2045,
+      "step": 179
+    },
+    {
+      "epoch": 0.9278350515463918,
+      "grad_norm": 1.140464084681919,
+      "learning_rate": 8.756309654875059e-06,
+      "loss": 0.3075,
+      "step": 180
+    },
+    {
+      "epoch": 0.9329896907216495,
+      "grad_norm": 1.1867468428900187,
+      "learning_rate": 8.736419211660054e-06,
+      "loss": 0.2445,
+      "step": 181
+    },
+    {
+      "epoch": 0.9381443298969072,
+      "grad_norm": 1.2294904183688709,
+      "learning_rate": 8.716393949582656e-06,
+      "loss": 0.2416,
+      "step": 182
+    },
+    {
+      "epoch": 0.9432989690721649,
+      "grad_norm": 0.7483697175175423,
+      "learning_rate": 8.696234591201793e-06,
+      "loss": 0.1126,
+      "step": 183
+    },
+    {
+      "epoch": 0.9484536082474226,
+      "grad_norm": 0.9739357119214708,
+      "learning_rate": 8.6759418639149e-06,
+      "loss": 0.167,
+      "step": 184
+    },
+    {
+      "epoch": 0.9536082474226805,
+      "grad_norm": 1.4251293577602404,
+      "learning_rate": 8.655516499931684e-06,
+      "loss": 0.3314,
+      "step": 185
+    },
+    {
+      "epoch": 0.9587628865979382,
+      "grad_norm": 1.140569606339371,
+      "learning_rate": 8.634959236247695e-06,
+      "loss": 0.2206,
+      "step": 186
+    },
+    {
+      "epoch": 0.9639175257731959,
+      "grad_norm": 0.9214436194181765,
+      "learning_rate": 8.61427081461774e-06,
+      "loss": 0.1622,
+      "step": 187
+    },
+    {
+      "epoch": 0.9690721649484536,
+      "grad_norm": 1.4025795614332346,
+      "learning_rate": 8.593451981529109e-06,
+      "loss": 0.2202,
+      "step": 188
+    },
+    {
+      "epoch": 0.9742268041237113,
+      "grad_norm": 0.7327985656704634,
+      "learning_rate": 8.572503488174655e-06,
+      "loss": 0.0798,
+      "step": 189
+    },
+    {
+      "epoch": 0.979381443298969,
+      "grad_norm": 1.1641896784338794,
+      "learning_rate": 8.551426090425678e-06,
+      "loss": 0.1978,
+      "step": 190
+    },
+    {
+      "epoch": 0.9845360824742269,
+      "grad_norm": 1.086213303235639,
+      "learning_rate": 8.53022054880465e-06,
+      "loss": 0.1558,
+      "step": 191
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 1.0472347005656282,
+      "learning_rate": 8.508887628457783e-06,
+      "loss": 0.2053,
+      "step": 192
+    },
+    {
+      "epoch": 0.9948453608247423,
+      "grad_norm": 0.7910662337183756,
+      "learning_rate": 8.487428099127411e-06,
+      "loss": 0.0927,
+      "step": 193
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.1006430197444728,
+      "learning_rate": 8.465842735124224e-06,
+      "loss": 0.1894,
+      "step": 194
+    },
+    {
+      "epoch": 1.0051546391752577,
+      "grad_norm": 0.5906742201713365,
+      "learning_rate": 8.444132315299321e-06,
+      "loss": 0.0537,
+      "step": 195
+    },
+    {
+      "epoch": 1.0103092783505154,
+      "grad_norm": 0.6751125368476019,
+      "learning_rate": 8.422297623016118e-06,
+      "loss": 0.0806,
+      "step": 196
+    },
+    {
+      "epoch": 1.0154639175257731,
+      "grad_norm": 1.0260689629426207,
+      "learning_rate": 8.40033944612207e-06,
+      "loss": 0.1132,
+      "step": 197
+    },
+    {
+      "epoch": 1.0206185567010309,
+      "grad_norm": 0.5551436381218386,
+      "learning_rate": 8.378258576920253e-06,
+      "loss": 0.0523,
+      "step": 198
+    },
+    {
+      "epoch": 1.0257731958762886,
+      "grad_norm": 0.6869421294596499,
+      "learning_rate": 8.356055812140768e-06,
+      "loss": 0.0907,
+      "step": 199
+    },
+    {
+      "epoch": 1.0309278350515463,
+      "grad_norm": 0.9886419404257938,
+      "learning_rate": 8.333731952912e-06,
+      "loss": 0.1147,
+      "step": 200
+    },
+    {
+      "epoch": 1.0360824742268042,
+      "grad_norm": 0.8201901345855567,
+      "learning_rate": 8.311287804731716e-06,
+      "loss": 0.053,
+      "step": 201
+    },
+    {
+      "epoch": 1.041237113402062,
+      "grad_norm": 0.6231211273936398,
+      "learning_rate": 8.288724177437976e-06,
+      "loss": 0.0558,
+      "step": 202
+    },
+    {
+      "epoch": 1.0463917525773196,
+      "grad_norm": 1.0979347326591262,
+      "learning_rate": 8.266041885179949e-06,
+      "loss": 0.1248,
+      "step": 203
+    },
+    {
+      "epoch": 1.0515463917525774,
+      "grad_norm": 1.0441782376710624,
+      "learning_rate": 8.243241746388504e-06,
+      "loss": 0.1024,
+      "step": 204
+    },
+    {
+      "epoch": 1.056701030927835,
+      "grad_norm": 0.8617708313835702,
+      "learning_rate": 8.220324583746697e-06,
+      "loss": 0.0864,
+      "step": 205
+    },
+    {
+      "epoch": 1.0618556701030928,
+      "grad_norm": 0.8219004811721925,
+      "learning_rate": 8.197291224160082e-06,
+      "loss": 0.0965,
+      "step": 206
+    },
+    {
+      "epoch": 1.0670103092783505,
+      "grad_norm": 1.446199673821668,
+      "learning_rate": 8.174142498726875e-06,
+      "loss": 0.1316,
+      "step": 207
+    },
+    {
+      "epoch": 1.0721649484536082,
+      "grad_norm": 0.9970004312056989,
+      "learning_rate": 8.150879242707963e-06,
+      "loss": 0.0785,
+      "step": 208
+    },
+    {
+      "epoch": 1.077319587628866,
+      "grad_norm": 0.6799947961502295,
+      "learning_rate": 8.127502295496768e-06,
+      "loss": 0.0546,
+      "step": 209
+    },
+    {
+      "epoch": 1.0824742268041236,
+      "grad_norm": 0.8459778750809145,
+      "learning_rate": 8.104012500588962e-06,
+      "loss": 0.0754,
+      "step": 210
+    },
+    {
+      "epoch": 1.0876288659793814,
+      "grad_norm": 0.8764373407801908,
+      "learning_rate": 8.080410705552028e-06,
+      "loss": 0.0725,
+      "step": 211
+    },
+    {
+      "epoch": 1.0927835051546393,
+      "grad_norm": 1.4250917004738353,
+      "learning_rate": 8.056697761994679e-06,
+      "loss": 0.1466,
+      "step": 212
+    },
+    {
+      "epoch": 1.097938144329897,
+      "grad_norm": 0.7470601320144464,
+      "learning_rate": 8.032874525536132e-06,
+      "loss": 0.0554,
+      "step": 213
+    },
+    {
+      "epoch": 1.1030927835051547,
+      "grad_norm": 0.7217791614950412,
+      "learning_rate": 8.008941855775228e-06,
+      "loss": 0.104,
+      "step": 214
+    },
+    {
+      "epoch": 1.1082474226804124,
+      "grad_norm": 1.018751301091875,
+      "learning_rate": 7.98490061625943e-06,
+      "loss": 0.1098,
+      "step": 215
+    },
+    {
+      "epoch": 1.1134020618556701,
+      "grad_norm": 0.8577713345259472,
+      "learning_rate": 7.960751674453644e-06,
+      "loss": 0.106,
+      "step": 216
+    },
+    {
+      "epoch": 1.1185567010309279,
+      "grad_norm": 0.7354671182870788,
+      "learning_rate": 7.93649590170894e-06,
+      "loss": 0.0776,
+      "step": 217
+    },
+    {
+      "epoch": 1.1237113402061856,
+      "grad_norm": 0.784080342118224,
+      "learning_rate": 7.912134173231099e-06,
+      "loss": 0.1065,
+      "step": 218
+    },
+    {
+      "epoch": 1.1288659793814433,
+      "grad_norm": 1.0447979386760058,
+      "learning_rate": 7.887667368049028e-06,
+      "loss": 0.1501,
+      "step": 219
+    },
+    {
+      "epoch": 1.134020618556701,
+      "grad_norm": 0.8251703086624239,
+      "learning_rate": 7.863096368983061e-06,
+      "loss": 0.0888,
+      "step": 220
+    },
+    {
+      "epoch": 1.1391752577319587,
+      "grad_norm": 0.8822362088146911,
+      "learning_rate": 7.838422062613088e-06,
+      "loss": 0.093,
+      "step": 221
+    },
+    {
+      "epoch": 1.1443298969072164,
+      "grad_norm": 0.8949834524497724,
+      "learning_rate": 7.813645339246578e-06,
+      "loss": 0.0921,
+      "step": 222
+    },
+    {
+      "epoch": 1.1494845360824741,
+      "grad_norm": 0.5374131970068409,
+      "learning_rate": 7.78876709288644e-06,
+      "loss": 0.0386,
+      "step": 223
+    },
+    {
+      "epoch": 1.1546391752577319,
+      "grad_norm": 0.7564742772338368,
+      "learning_rate": 7.763788221198775e-06,
+      "loss": 0.0948,
+      "step": 224
+    },
+    {
+      "epoch": 1.1597938144329896,
+      "grad_norm": 0.8808313875725176,
+      "learning_rate": 7.738709625480494e-06,
+      "loss": 0.092,
+      "step": 225
+    },
+    {
+      "epoch": 1.1649484536082475,
+      "grad_norm": 0.6478248778597727,
+      "learning_rate": 7.713532210626771e-06,
+      "loss": 0.0458,
+      "step": 226
+    },
+    {
+      "epoch": 1.1701030927835052,
+      "grad_norm": 0.9288097880385096,
+      "learning_rate": 7.68825688509842e-06,
+      "loss": 0.0894,
+      "step": 227
+    },
+    {
+      "epoch": 1.175257731958763,
+      "grad_norm": 0.714867355071131,
+      "learning_rate": 7.662884560889106e-06,
+      "loss": 0.0541,
+      "step": 228
+    },
+    {
+      "epoch": 1.1804123711340206,
+      "grad_norm": 0.6642395918740392,
+      "learning_rate": 7.637416153492426e-06,
+      "loss": 0.0663,
+      "step": 229
+    },
+    {
+      "epoch": 1.1855670103092784,
+      "grad_norm": 0.9527549900666177,
+      "learning_rate": 7.611852581868895e-06,
+      "loss": 0.1443,
+      "step": 230
+    },
+    {
+      "epoch": 1.190721649484536,
+      "grad_norm": 0.7893883831371513,
+      "learning_rate": 7.586194768412778e-06,
+      "loss": 0.0872,
+      "step": 231
+    },
+    {
+      "epoch": 1.1958762886597938,
+      "grad_norm": 0.9884146330428806,
+      "learning_rate": 7.560443638918801e-06,
+      "loss": 0.0821,
+      "step": 232
+    },
+    {
+      "epoch": 1.2010309278350515,
+      "grad_norm": 0.7413524893904028,
+      "learning_rate": 7.534600122548766e-06,
+      "loss": 0.1001,
+      "step": 233
+    },
+    {
+      "epoch": 1.2061855670103092,
+      "grad_norm": 0.6487178792290845,
+      "learning_rate": 7.508665151798e-06,
+      "loss": 0.0669,
+      "step": 234
+    },
+    {
+      "epoch": 1.211340206185567,
+      "grad_norm": 1.2033223139705194,
+      "learning_rate": 7.482639662461731e-06,
+      "loss": 0.1102,
+      "step": 235
+    },
+    {
+      "epoch": 1.2164948453608249,
+      "grad_norm": 1.1496624331229564,
+      "learning_rate": 7.456524593601306e-06,
+      "loss": 0.0817,
+      "step": 236
+    },
+    {
+      "epoch": 1.2216494845360826,
+      "grad_norm": 0.8048271397849805,
+      "learning_rate": 7.430320887510319e-06,
+      "loss": 0.066,
+      "step": 237
+    },
+    {
+      "epoch": 1.2268041237113403,
+      "grad_norm": 1.0865257986253214,
+      "learning_rate": 7.404029489680597e-06,
+      "loss": 0.1054,
+      "step": 238
+    },
+    {
+      "epoch": 1.231958762886598,
+      "grad_norm": 0.9118222773920444,
+      "learning_rate": 7.377651348768102e-06,
+      "loss": 0.0734,
+      "step": 239
+    },
+    {
+      "epoch": 1.2371134020618557,
+      "grad_norm": 0.7111948595434698,
+      "learning_rate": 7.351187416558686e-06,
+      "loss": 0.0455,
+      "step": 240
+    },
+    {
+      "epoch": 1.2422680412371134,
+      "grad_norm": 1.1586255328358697,
+      "learning_rate": 7.324638647933756e-06,
+      "loss": 0.1247,
+      "step": 241
+    },
+    {
+      "epoch": 1.2474226804123711,
+      "grad_norm": 0.7885336165369894,
+      "learning_rate": 7.29800600083582e-06,
+      "loss": 0.0944,
+      "step": 242
+    },
+    {
+      "epoch": 1.2525773195876289,
+      "grad_norm": 0.815328204346094,
+      "learning_rate": 7.2712904362339155e-06,
+      "loss": 0.0846,
+      "step": 243
+    },
+    {
+      "epoch": 1.2577319587628866,
+      "grad_norm": 1.044831188842817,
+      "learning_rate": 7.244492918088946e-06,
+      "loss": 0.1029,
+      "step": 244
+    },
+    {
+      "epoch": 1.2628865979381443,
+      "grad_norm": 1.1074505493277451,
+      "learning_rate": 7.217614413318887e-06,
+      "loss": 0.1109,
+      "step": 245
+    },
+    {
+      "epoch": 1.268041237113402,
+      "grad_norm": 0.836136628649968,
+      "learning_rate": 7.19065589176391e-06,
+      "loss": 0.1074,
+      "step": 246
+    },
+    {
+      "epoch": 1.2731958762886597,
+      "grad_norm": 0.9806183729514004,
+      "learning_rate": 7.1636183261513784e-06,
+      "loss": 0.1046,
+      "step": 247
+    },
+    {
+      "epoch": 1.2783505154639174,
+      "grad_norm": 0.8666879067703104,
+      "learning_rate": 7.136502692060746e-06,
+      "loss": 0.0826,
+      "step": 248
+    },
+    {
+      "epoch": 1.2835051546391751,
+      "grad_norm": 0.801232774030085,
+      "learning_rate": 7.109309967888376e-06,
+      "loss": 0.0556,
+      "step": 249
+    },
+    {
+      "epoch": 1.2886597938144329,
+      "grad_norm": 1.1897623094936245,
+      "learning_rate": 7.0820411348122144e-06,
+      "loss": 0.154,
+      "step": 250
+    },
+    {
+      "epoch": 1.2938144329896908,
+      "grad_norm": 0.8276583732971441,
+      "learning_rate": 7.0546971767564e-06,
+      "loss": 0.0833,
+      "step": 251
+    },
+    {
+      "epoch": 1.2989690721649485,
+      "grad_norm": 0.7583663543944267,
+      "learning_rate": 7.027279080355756e-06,
+      "loss": 0.0499,
+      "step": 252
+    },
+    {
+      "epoch": 1.3041237113402062,
+      "grad_norm": 0.8649391169592322,
+      "learning_rate": 6.999787834920202e-06,
+      "loss": 0.0867,
+      "step": 253
+    },
+    {
+      "epoch": 1.309278350515464,
+      "grad_norm": 1.0915318471452742,
+      "learning_rate": 6.972224432399038e-06,
+      "loss": 0.0676,
+      "step": 254
+    },
+    {
+      "epoch": 1.3144329896907216,
+      "grad_norm": 1.0231154625513728,
+      "learning_rate": 6.9445898673451635e-06,
+      "loss": 0.1028,
+      "step": 255
+    },
+    {
+      "epoch": 1.3195876288659794,
+      "grad_norm": 0.933663875875191,
+      "learning_rate": 6.916885136879197e-06,
+      "loss": 0.0967,
+      "step": 256
+    },
+    {
+      "epoch": 1.324742268041237,
+      "grad_norm": 0.8912988511114369,
+      "learning_rate": 6.889111240653488e-06,
+      "loss": 0.0959,
+      "step": 257
+    },
+    {
+      "epoch": 1.3298969072164948,
+      "grad_norm": 0.8687955070867821,
+      "learning_rate": 6.861269180816052e-06,
+      "loss": 0.0977,
+      "step": 258
+    },
+    {
+      "epoch": 1.3350515463917525,
+      "grad_norm": 0.7106326271334324,
+      "learning_rate": 6.833359961974406e-06,
+      "loss": 0.0869,
+      "step": 259
+    },
+    {
+      "epoch": 1.3402061855670104,
+      "grad_norm": 0.9501736705275039,
+      "learning_rate": 6.805384591159325e-06,
+      "loss": 0.0949,
+      "step": 260
+    },
+    {
+      "epoch": 1.3453608247422681,
+      "grad_norm": 0.804663253737915,
+      "learning_rate": 6.7773440777885055e-06,
+      "loss": 0.0811,
+      "step": 261
+    },
+    {
+      "epoch": 1.3505154639175259,
+      "grad_norm": 0.6042006243936727,
+      "learning_rate": 6.749239433630137e-06,
+      "loss": 0.0537,
+      "step": 262
+    },
+    {
+      "epoch": 1.3556701030927836,
+      "grad_norm": 1.1315557610677505,
+      "learning_rate": 6.721071672766407e-06,
+      "loss": 0.1242,
+      "step": 263
+    },
+    {
+      "epoch": 1.3608247422680413,
+      "grad_norm": 0.664551606971833,
+      "learning_rate": 6.6928418115568994e-06,
+      "loss": 0.05,
+      "step": 264
+    },
+    {
+      "epoch": 1.365979381443299,
+      "grad_norm": 0.6628232247101428,
+      "learning_rate": 6.6645508686019225e-06,
+      "loss": 0.0709,
+      "step": 265
+    },
+    {
+      "epoch": 1.3711340206185567,
+      "grad_norm": 1.3704143398811302,
+      "learning_rate": 6.636199864705766e-06,
+      "loss": 0.1788,
+      "step": 266
+    },
+    {
+      "epoch": 1.3762886597938144,
+      "grad_norm": 0.653208777448595,
+      "learning_rate": 6.607789822839855e-06,
+      "loss": 0.0605,
+      "step": 267
+    },
+    {
+      "epoch": 1.3814432989690721,
+      "grad_norm": 0.7238199007998108,
+      "learning_rate": 6.579321768105845e-06,
+      "loss": 0.081,
+      "step": 268
+    },
+    {
+      "epoch": 1.3865979381443299,
+      "grad_norm": 0.7205533607672164,
+      "learning_rate": 6.550796727698639e-06,
+      "loss": 0.067,
+      "step": 269
+    },
+    {
+      "epoch": 1.3917525773195876,
+      "grad_norm": 0.6700885764195117,
+      "learning_rate": 6.52221573086931e-06,
+      "loss": 0.0503,
+      "step": 270
+    },
+    {
+      "epoch": 1.3969072164948453,
+      "grad_norm": 1.219456301028477,
+      "learning_rate": 6.493579808887976e-06,
+      "loss": 0.1329,
+      "step": 271
+    },
+    {
+      "epoch": 1.402061855670103,
+      "grad_norm": 1.327064144446766,
+      "learning_rate": 6.4648899950065865e-06,
+      "loss": 0.1581,
+      "step": 272
+    },
+    {
+      "epoch": 1.4072164948453607,
+      "grad_norm": 0.8319301363228734,
+      "learning_rate": 6.436147324421635e-06,
+      "loss": 0.0867,
+      "step": 273
+    },
+    {
+      "epoch": 1.4123711340206184,
+      "grad_norm": 1.1371748524536707,
+      "learning_rate": 6.407352834236807e-06,
+      "loss": 0.1496,
+      "step": 274
+    },
+    {
+      "epoch": 1.4175257731958764,
+      "grad_norm": 0.856128052640479,
+      "learning_rate": 6.378507563425571e-06,
+      "loss": 0.0804,
+      "step": 275
+    },
+    {
+      "epoch": 1.422680412371134,
+      "grad_norm": 1.062404018021394,
+      "learning_rate": 6.349612552793675e-06,
+      "loss": 0.1043,
+      "step": 276
+    },
+    {
+      "epoch": 1.4278350515463918,
+      "grad_norm": 0.9101560194006858,
+      "learning_rate": 6.320668844941598e-06,
+      "loss": 0.1002,
+      "step": 277
+    },
+    {
+      "epoch": 1.4329896907216495,
+      "grad_norm": 1.2757033041145538,
+      "learning_rate": 6.291677484226929e-06,
+      "loss": 0.1098,
+      "step": 278
+    },
+    {
+      "epoch": 1.4381443298969072,
+      "grad_norm": 1.2846837622920635,
+      "learning_rate": 6.26263951672669e-06,
+      "loss": 0.1197,
+      "step": 279
+    },
+    {
+      "epoch": 1.443298969072165,
+      "grad_norm": 0.6126591325904064,
+      "learning_rate": 6.233555990199583e-06,
+      "loss": 0.0526,
+      "step": 280
+    },
+    {
+      "epoch": 1.4484536082474226,
+      "grad_norm": 0.9201467393931315,
+      "learning_rate": 6.204427954048186e-06,
+      "loss": 0.095,
+      "step": 281
+    },
+    {
+      "epoch": 1.4536082474226804,
+      "grad_norm": 0.8709260663548162,
+      "learning_rate": 6.175256459281093e-06,
+      "loss": 0.0956,
+      "step": 282
+    },
+    {
+      "epoch": 1.458762886597938,
+      "grad_norm": 0.8394883872798908,
+      "learning_rate": 6.146042558474987e-06,
+      "loss": 0.0782,
+      "step": 283
+    },
+    {
+      "epoch": 1.463917525773196,
+      "grad_norm": 0.7647943393509891,
+      "learning_rate": 6.116787305736659e-06,
+      "loss": 0.0964,
+      "step": 284
+    },
+    {
+      "epoch": 1.4690721649484537,
+      "grad_norm": 1.1981279245762775,
+      "learning_rate": 6.087491756664982e-06,
+      "loss": 0.1251,
+      "step": 285
+    },
+    {
+      "epoch": 1.4742268041237114,
+      "grad_norm": 0.7281773116566167,
+      "learning_rate": 6.058156968312808e-06,
+      "loss": 0.0636,
+      "step": 286
+    },
+    {
+      "epoch": 1.4793814432989691,
+      "grad_norm": 0.9415282186895138,
+      "learning_rate": 6.028783999148841e-06,
+      "loss": 0.121,
+      "step": 287
+    },
+    {
+      "epoch": 1.4845360824742269,
+      "grad_norm": 0.8155749049438948,
+      "learning_rate": 5.999373909019437e-06,
+      "loss": 0.0607,
+      "step": 288
+    },
+    {
+      "epoch": 1.4896907216494846,
+      "grad_norm": 0.7639944315517929,
+      "learning_rate": 5.9699277591103665e-06,
+      "loss": 0.0548,
+      "step": 289
+    },
+    {
+      "epoch": 1.4948453608247423,
+      "grad_norm": 0.8636520383698243,
+      "learning_rate": 5.940446611908519e-06,
+      "loss": 0.0979,
+      "step": 290
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5326124314349575,
+      "learning_rate": 5.91093153116357e-06,
+      "loss": 0.0373,
+      "step": 291
+    },
+    {
+      "epoch": 1.5051546391752577,
+      "grad_norm": 0.8280155720382041,
+      "learning_rate": 5.881383581849601e-06,
+      "loss": 0.0698,
+      "step": 292
+    },
+    {
+      "epoch": 1.5103092783505154,
+      "grad_norm": 0.9092824338400287,
+      "learning_rate": 5.851803830126666e-06,
+      "loss": 0.1016,
+      "step": 293
+    },
+    {
+      "epoch": 1.5154639175257731,
+      "grad_norm": 1.2564418341193255,
+      "learning_rate": 5.822193343302328e-06,
+      "loss": 0.1473,
+      "step": 294
+    },
+    {
+      "epoch": 1.5206185567010309,
+      "grad_norm": 0.8983314520281567,
+      "learning_rate": 5.792553189793141e-06,
+      "loss": 0.1071,
+      "step": 295
+    },
+    {
+      "epoch": 1.5257731958762886,
+      "grad_norm": 0.9871176927471953,
+      "learning_rate": 5.762884439086108e-06,
+      "loss": 0.1235,
+      "step": 296
+    },
+    {
+      "epoch": 1.5309278350515463,
+      "grad_norm": 1.0212569217738547,
+      "learning_rate": 5.733188161700084e-06,
+      "loss": 0.1144,
+      "step": 297
+    },
+    {
+      "epoch": 1.536082474226804,
+      "grad_norm": 1.0505577277639713,
+      "learning_rate": 5.703465429147153e-06,
+      "loss": 0.0856,
+      "step": 298
+    },
+    {
+      "epoch": 1.5412371134020617,
+      "grad_norm": 0.9198501514769984,
+      "learning_rate": 5.673717313893963e-06,
+      "loss": 0.0857,
+      "step": 299
+    },
+    {
+      "epoch": 1.5463917525773194,
+      "grad_norm": 0.4413128663709364,
+      "learning_rate": 5.643944889323031e-06,
+      "loss": 0.0339,
+      "step": 300
+    },
+    {
+      "epoch": 1.5515463917525774,
+      "grad_norm": 0.9176541299396651,
+      "learning_rate": 5.6141492296940104e-06,
+      "loss": 0.0883,
+      "step": 301
+    },
+    {
+      "epoch": 1.556701030927835,
+      "grad_norm": 0.4947875542348694,
+      "learning_rate": 5.584331410104934e-06,
+      "loss": 0.0282,
+      "step": 302
+    },
+    {
+      "epoch": 1.5618556701030928,
+      "grad_norm": 1.1769881441147931,
+      "learning_rate": 5.554492506453415e-06,
+      "loss": 0.1418,
+      "step": 303
+    },
+    {
+      "epoch": 1.5670103092783505,
+      "grad_norm": 0.8273504464851464,
+      "learning_rate": 5.524633595397829e-06,
+      "loss": 0.0639,
+      "step": 304
+    },
+    {
+      "epoch": 1.5721649484536082,
+      "grad_norm": 1.104084036749989,
+      "learning_rate": 5.494755754318472e-06,
+      "loss": 0.1496,
+      "step": 305
+    },
+    {
+      "epoch": 1.577319587628866,
+      "grad_norm": 0.722149475333966,
+      "learning_rate": 5.464860061278673e-06,
+      "loss": 0.06,
+      "step": 306
+    },
+    {
+      "epoch": 1.5824742268041239,
+      "grad_norm": 0.765678640808434,
+      "learning_rate": 5.434947594985903e-06,
+      "loss": 0.064,
+      "step": 307
+    },
+    {
+      "epoch": 1.5876288659793816,
+      "grad_norm": 0.8133799235994497,
+      "learning_rate": 5.40501943475286e-06,
+      "loss": 0.0834,
+      "step": 308
+    },
+    {
+      "epoch": 1.5927835051546393,
+      "grad_norm": 1.0133768144130846,
+      "learning_rate": 5.375076660458503e-06,
+      "loss": 0.1211,
+      "step": 309
+    },
+    {
+      "epoch": 1.597938144329897,
+      "grad_norm": 0.8911686618887108,
+      "learning_rate": 5.345120352509114e-06,
+      "loss": 0.1135,
+      "step": 310
+    },
+    {
+      "epoch": 1.6030927835051547,
+      "grad_norm": 0.9837172309407369,
+      "learning_rate": 5.315151591799293e-06,
+      "loss": 0.0939,
+      "step": 311
+    },
+    {
+      "epoch": 1.6082474226804124,
+      "grad_norm": 0.9603201029901375,
+      "learning_rate": 5.28517145967297e-06,
+      "loss": 0.1191,
+      "step": 312
+    },
+    {
+      "epoch": 1.6134020618556701,
+      "grad_norm": 0.7568038226377672,
+      "learning_rate": 5.255181037884377e-06,
+      "loss": 0.0878,
+      "step": 313
+    },
+    {
+      "epoch": 1.6185567010309279,
+      "grad_norm": 0.7396794148405889,
+      "learning_rate": 5.225181408559028e-06,
+      "loss": 0.0713,
+      "step": 314
+    },
+    {
+      "epoch": 1.6237113402061856,
+      "grad_norm": 0.8098683954087241,
+      "learning_rate": 5.195173654154662e-06,
+      "loss": 0.06,
+      "step": 315
+    },
+    {
+      "epoch": 1.6288659793814433,
+      "grad_norm": 0.9687294980139846,
+      "learning_rate": 5.165158857422191e-06,
+      "loss": 0.0856,
+      "step": 316
+    },
+    {
+      "epoch": 1.634020618556701,
+      "grad_norm": 0.991898312261934,
+      "learning_rate": 5.135138101366633e-06,
+      "loss": 0.1205,
+      "step": 317
+    },
+    {
+      "epoch": 1.6391752577319587,
+      "grad_norm": 0.5573665413209947,
+      "learning_rate": 5.105112469208032e-06,
+      "loss": 0.0497,
+      "step": 318
+    },
+    {
+      "epoch": 1.6443298969072164,
+      "grad_norm": 1.0382601563430964,
+      "learning_rate": 5.075083044342371e-06,
+      "loss": 0.0852,
+      "step": 319
+    },
+    {
+      "epoch": 1.6494845360824741,
+      "grad_norm": 0.9967396087063322,
+      "learning_rate": 5.045050910302485e-06,
+      "loss": 0.0877,
+      "step": 320
+    },
+    {
+      "epoch": 1.6546391752577319,
+      "grad_norm": 0.7962058373120292,
+      "learning_rate": 5.015017150718961e-06,
+      "loss": 0.0837,
+      "step": 321
+    },
+    {
+      "epoch": 1.6597938144329896,
+      "grad_norm": 0.6489956586111506,
+      "learning_rate": 4.984982849281041e-06,
+      "loss": 0.0394,
+      "step": 322
+    },
+    {
+      "epoch": 1.6649484536082473,
+      "grad_norm": 0.6615424807101872,
+      "learning_rate": 4.9549490896975175e-06,
+      "loss": 0.0507,
+      "step": 323
+    },
+    {
+      "epoch": 1.670103092783505,
+      "grad_norm": 1.0065188138819108,
+      "learning_rate": 4.92491695565763e-06,
+      "loss": 0.0913,
+      "step": 324
+    },
+    {
+      "epoch": 1.675257731958763,
+      "grad_norm": 0.9338664154455895,
+      "learning_rate": 4.894887530791968e-06,
+      "loss": 0.0829,
+      "step": 325
+    },
+    {
+      "epoch": 1.6804123711340206,
+      "grad_norm": 0.8619735255759078,
+      "learning_rate": 4.864861898633367e-06,
+      "loss": 0.1015,
+      "step": 326
+    },
+    {
+      "epoch": 1.6855670103092784,
+      "grad_norm": 1.1629690007707925,
+      "learning_rate": 4.8348411425778105e-06,
+      "loss": 0.1093,
+      "step": 327
+    },
+    {
+      "epoch": 1.690721649484536,
+      "grad_norm": 0.8508681932219984,
+      "learning_rate": 4.80482634584534e-06,
+      "loss": 0.0787,
+      "step": 328
+    },
+    {
+      "epoch": 1.6958762886597938,
+      "grad_norm": 0.7692449841056024,
+      "learning_rate": 4.774818591440974e-06,
+      "loss": 0.0958,
+      "step": 329
+    },
+    {
+      "epoch": 1.7010309278350515,
+      "grad_norm": 0.8553151177506546,
+      "learning_rate": 4.744818962115624e-06,
+      "loss": 0.082,
+      "step": 330
+    },
+    {
+      "epoch": 1.7061855670103094,
+      "grad_norm": 0.5903484968058315,
+      "learning_rate": 4.714828540327033e-06,
+      "loss": 0.0462,
+      "step": 331
+    },
+    {
+      "epoch": 1.7113402061855671,
+      "grad_norm": 0.8864451372917644,
+      "learning_rate": 4.684848408200707e-06,
+      "loss": 0.0714,
+      "step": 332
+    },
+    {
+      "epoch": 1.7164948453608249,
+      "grad_norm": 0.8860344350682171,
+      "learning_rate": 4.654879647490887e-06,
+      "loss": 0.0691,
+      "step": 333
+    },
+    {
+      "epoch": 1.7216494845360826,
+      "grad_norm": 0.8183534311660873,
+      "learning_rate": 4.624923339541498e-06,
+      "loss": 0.0633,
+      "step": 334
+    },
+    {
+      "epoch": 1.7268041237113403,
+      "grad_norm": 0.614568204141328,
+      "learning_rate": 4.594980565247143e-06,
+      "loss": 0.0495,
+      "step": 335
+    },
+    {
+      "epoch": 1.731958762886598,
+      "grad_norm": 0.9930144229307591,
+      "learning_rate": 4.565052405014098e-06,
+      "loss": 0.1059,
+      "step": 336
+    },
+    {
+      "epoch": 1.7371134020618557,
+      "grad_norm": 0.7592312136391701,
+      "learning_rate": 4.5351399387213305e-06,
+      "loss": 0.0618,
+      "step": 337
+    },
+    {
+      "epoch": 1.7422680412371134,
+      "grad_norm": 1.4380591077584624,
+      "learning_rate": 4.5052442456815294e-06,
+      "loss": 0.0997,
+      "step": 338
+    },
+    {
+      "epoch": 1.7474226804123711,
+      "grad_norm": 0.9459809494967879,
+      "learning_rate": 4.47536640460217e-06,
+      "loss": 0.1004,
+      "step": 339
+    },
+    {
+      "epoch": 1.7525773195876289,
+      "grad_norm": 0.7417698139276238,
+      "learning_rate": 4.445507493546586e-06,
+      "loss": 0.0805,
+      "step": 340
+    },
+    {
+      "epoch": 1.7577319587628866,
+      "grad_norm": 0.8768339149771931,
+      "learning_rate": 4.4156685898950676e-06,
+      "loss": 0.0892,
+      "step": 341
+    },
+    {
+      "epoch": 1.7628865979381443,
+      "grad_norm": 0.5753560085161841,
+      "learning_rate": 4.385850770305991e-06,
+      "loss": 0.0546,
+      "step": 342
+    },
+    {
+      "epoch": 1.768041237113402,
+      "grad_norm": 0.6203625417079575,
+      "learning_rate": 4.356055110676971e-06,
+      "loss": 0.0557,
+      "step": 343
+    },
+    {
+      "epoch": 1.7731958762886597,
+      "grad_norm": 1.290592433705904,
+      "learning_rate": 4.326282686106039e-06,
+      "loss": 0.0924,
+      "step": 344
+    },
+    {
+      "epoch": 1.7783505154639174,
+      "grad_norm": 0.8501802343729535,
+      "learning_rate": 4.296534570852848e-06,
+      "loss": 0.0976,
+      "step": 345
+    },
+    {
+      "epoch": 1.7835051546391751,
+      "grad_norm": 0.7589958862583852,
+      "learning_rate": 4.266811838299916e-06,
+      "loss": 0.0616,
+      "step": 346
+    },
+    {
+      "epoch": 1.7886597938144329,
+      "grad_norm": 0.6634970203515521,
+      "learning_rate": 4.237115560913894e-06,
+      "loss": 0.0547,
+      "step": 347
+    },
+    {
+      "epoch": 1.7938144329896906,
+      "grad_norm": 0.7377540659991918,
+      "learning_rate": 4.20744681020686e-06,
+      "loss": 0.0562,
+      "step": 348
+    },
+    {
+      "epoch": 1.7989690721649485,
+      "grad_norm": 1.0154222900360976,
+      "learning_rate": 4.1778066566976736e-06,
+      "loss": 0.0889,
+      "step": 349
+    },
+    {
+      "epoch": 1.8041237113402062,
+      "grad_norm": 1.1675640094076947,
+      "learning_rate": 4.148196169873335e-06,
+      "loss": 0.1241,
+      "step": 350
+    },
+    {
+      "epoch": 1.809278350515464,
+      "grad_norm": 0.5783006867375596,
+      "learning_rate": 4.118616418150398e-06,
+      "loss": 0.0371,
+      "step": 351
+    },
+    {
+      "epoch": 1.8144329896907216,
+      "grad_norm": 1.067759818874075,
+      "learning_rate": 4.089068468836431e-06,
+      "loss": 0.1045,
+      "step": 352
+    },
+    {
+      "epoch": 1.8195876288659794,
+      "grad_norm": 0.8301529919273785,
+      "learning_rate": 4.059553388091483e-06,
+      "loss": 0.0907,
+      "step": 353
+    },
+    {
+      "epoch": 1.824742268041237,
+      "grad_norm": 0.8633283627168938,
+      "learning_rate": 4.030072240889635e-06,
+      "loss": 0.0883,
+      "step": 354
+    },
+    {
+      "epoch": 1.829896907216495,
+      "grad_norm": 1.0045407842411636,
+      "learning_rate": 4.000626090980564e-06,
+      "loss": 0.109,
+      "step": 355
+    },
+    {
+      "epoch": 1.8350515463917527,
+      "grad_norm": 0.6176720353760472,
+      "learning_rate": 3.971216000851161e-06,
+      "loss": 0.046,
+      "step": 356
+    },
+    {
+      "epoch": 1.8402061855670104,
+      "grad_norm": 0.6741212952732083,
+      "learning_rate": 3.941843031687194e-06,
+      "loss": 0.0616,
+      "step": 357
+    },
+    {
+      "epoch": 1.8453608247422681,
+      "grad_norm": 0.786429607982951,
+      "learning_rate": 3.912508243335019e-06,
+      "loss": 0.0814,
+      "step": 358
+    },
+    {
+      "epoch": 1.8505154639175259,
+      "grad_norm": 0.7681340177017846,
+      "learning_rate": 3.883212694263341e-06,
+      "loss": 0.0413,
+      "step": 359
+    },
+    {
+      "epoch": 1.8556701030927836,
+      "grad_norm": 0.9188584907010531,
+      "learning_rate": 3.853957441525014e-06,
+      "loss": 0.0917,
+      "step": 360
+    },
+    {
+      "epoch": 1.8608247422680413,
+      "grad_norm": 0.7339463471541188,
+      "learning_rate": 3.824743540718909e-06,
+      "loss": 0.0518,
+      "step": 361
+    },
+    {
+      "epoch": 1.865979381443299,
+      "grad_norm": 0.7505002518495965,
+      "learning_rate": 3.7955720459518163e-06,
+      "loss": 0.0611,
+      "step": 362
+    },
+    {
+      "epoch": 1.8711340206185567,
+      "grad_norm": 0.6977481350680906,
+      "learning_rate": 3.7664440098004194e-06,
+      "loss": 0.0662,
+      "step": 363
+    },
+    {
+      "epoch": 1.8762886597938144,
+      "grad_norm": 0.9305995047119137,
+      "learning_rate": 3.7373604832733103e-06,
+      "loss": 0.1134,
+      "step": 364
+    },
+    {
+      "epoch": 1.8814432989690721,
+      "grad_norm": 0.838945380538262,
+      "learning_rate": 3.708322515773071e-06,
+      "loss": 0.0848,
+      "step": 365
+    },
+    {
+      "epoch": 1.8865979381443299,
+      "grad_norm": 0.950916164653827,
+      "learning_rate": 3.6793311550584043e-06,
+      "loss": 0.0848,
+      "step": 366
+    },
+    {
+      "epoch": 1.8917525773195876,
+      "grad_norm": 0.8218742627036616,
+      "learning_rate": 3.6503874472063268e-06,
+      "loss": 0.1023,
+      "step": 367
+    },
+    {
+      "epoch": 1.8969072164948453,
+      "grad_norm": 0.9078783194850608,
+      "learning_rate": 3.62149243657443e-06,
+      "loss": 0.0931,
+      "step": 368
+    },
+    {
+      "epoch": 1.902061855670103,
+      "grad_norm": 0.688660913780332,
+      "learning_rate": 3.5926471657631945e-06,
+      "loss": 0.0589,
+      "step": 369
+    },
+    {
+      "epoch": 1.9072164948453607,
+      "grad_norm": 0.6952675588410017,
+      "learning_rate": 3.563852675578368e-06,
+      "loss": 0.0502,
+      "step": 370
+    },
+    {
+      "epoch": 1.9123711340206184,
+      "grad_norm": 1.3884427251376699,
+      "learning_rate": 3.535110004993414e-06,
+      "loss": 0.1733,
+      "step": 371
+    },
+    {
+      "epoch": 1.9175257731958761,
+      "grad_norm": 1.0258997166309576,
+      "learning_rate": 3.506420191112023e-06,
+      "loss": 0.1182,
+      "step": 372
+    },
+    {
+      "epoch": 1.922680412371134,
+      "grad_norm": 0.6919148043225545,
+      "learning_rate": 3.477784269130691e-06,
+      "loss": 0.07,
+      "step": 373
+    },
+    {
+      "epoch": 1.9278350515463918,
+      "grad_norm": 0.9093312963775791,
+      "learning_rate": 3.449203272301362e-06,
+      "loss": 0.0967,
+      "step": 374
+    },
+    {
+      "epoch": 1.9329896907216495,
+      "grad_norm": 0.8167616489115295,
+      "learning_rate": 3.4206782318941556e-06,
+      "loss": 0.0586,
+      "step": 375
+    },
+    {
+      "epoch": 1.9381443298969072,
+      "grad_norm": 0.8922256610004783,
+      "learning_rate": 3.3922101771601475e-06,
+      "loss": 0.0716,
+      "step": 376
+    },
+    {
+      "epoch": 1.943298969072165,
+      "grad_norm": 1.0215655504364405,
+      "learning_rate": 3.363800135294236e-06,
+      "loss": 0.1191,
+      "step": 377
+    },
+    {
+      "epoch": 1.9484536082474226,
+      "grad_norm": 1.3202130028849257,
+      "learning_rate": 3.3354491313980774e-06,
+      "loss": 0.1322,
+      "step": 378
+    },
+    {
+      "epoch": 1.9536082474226806,
+      "grad_norm": 1.0653863680738789,
+      "learning_rate": 3.3071581884431014e-06,
+      "loss": 0.1362,
+      "step": 379
+    },
+    {
+      "epoch": 1.9587628865979383,
+      "grad_norm": 0.7846807384773636,
+      "learning_rate": 3.2789283272335935e-06,
+      "loss": 0.0823,
+      "step": 380
+    },
+    {
+      "epoch": 1.963917525773196,
+      "grad_norm": 1.005891449118457,
+      "learning_rate": 3.250760566369864e-06,
+      "loss": 0.1152,
+      "step": 381
+    },
+    {
+      "epoch": 1.9690721649484537,
+      "grad_norm": 0.8386229662220965,
+      "learning_rate": 3.2226559222114974e-06,
+      "loss": 0.0743,
+      "step": 382
+    },
+    {
+      "epoch": 1.9742268041237114,
+      "grad_norm": 0.8015266394615227,
+      "learning_rate": 3.194615408840678e-06,
+      "loss": 0.0818,
+      "step": 383
+    },
+    {
+      "epoch": 1.9793814432989691,
+      "grad_norm": 1.1193048769312743,
+      "learning_rate": 3.1666400380255944e-06,
+      "loss": 0.156,
+      "step": 384
+    },
+    {
+      "epoch": 1.9845360824742269,
+      "grad_norm": 0.8507066467744703,
+      "learning_rate": 3.1387308191839495e-06,
+      "loss": 0.0967,
+      "step": 385
+    },
+    {
+      "epoch": 1.9896907216494846,
+      "grad_norm": 0.6565071516482492,
+      "learning_rate": 3.110888759346512e-06,
+      "loss": 0.0469,
+      "step": 386
+    },
+    {
+      "epoch": 1.9948453608247423,
+      "grad_norm": 0.7510076309546407,
+      "learning_rate": 3.0831148631208043e-06,
+      "loss": 0.0607,
+      "step": 387
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.9275588340131792,
+      "learning_rate": 3.055410132654838e-06,
+      "loss": 0.0939,
+      "step": 388
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 582,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 128421150621696.0,
+  "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:b573028e7d55b1fddbead52f1e1ef8b3944e95dca1156b751452464f7d8d9171
+size 8145

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)