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 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

latest

@@ -0,0 +1 @@
+global_step270

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b997082106e78eaed460b93d874cc4baab4aa514ba7eadaee385d63d81c70f77
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9c21a8df166f2ab99c72a436ddf22a2fe96c5f4e5aee21c8b2a8fc882e78b79
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92cc13315f24c28015d695b6cde08bb1cd6fea4cbc435998485ed6fbe4c91285
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c154b6a63e0b1f98f7d2847944398f99f1657d35e8eddf7fdf0ae2c24b0552
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784c6a9507b51189f2caffbd178ea9882103b75852e31c15f47fdae6a43af1d
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b023e05bc2d12b91dc436d4922b990d50ec8dc56d40dc3e36b3bb34fc81341
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f3e116edc7a4aaa795aa9d3305091b5d05b0faddc16441ba43419650b2148e
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1931 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 271,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0037011334721258385,
+      "grad_norm": 18.58395767211914,
+      "learning_rate": 0.0,
+      "loss": 2.0386,
+      "step": 1
+    },
+    {
+      "epoch": 0.007402266944251677,
+      "grad_norm": 18.265050888061523,
+      "learning_rate": 2.439024390243903e-07,
+      "loss": 2.0567,
+      "step": 2
+    },
+    {
+      "epoch": 0.011103400416377515,
+      "grad_norm": 17.878551483154297,
+      "learning_rate": 4.878048780487805e-07,
+      "loss": 2.0552,
+      "step": 3
+    },
+    {
+      "epoch": 0.014804533888503354,
+      "grad_norm": 16.966453552246094,
+      "learning_rate": 7.317073170731707e-07,
+      "loss": 2.0109,
+      "step": 4
+    },
+    {
+      "epoch": 0.018505667360629193,
+      "grad_norm": 16.161401748657227,
+      "learning_rate": 9.75609756097561e-07,
+      "loss": 1.9672,
+      "step": 5
+    },
+    {
+      "epoch": 0.02220680083275503,
+      "grad_norm": 15.977458953857422,
+      "learning_rate": 1.2195121951219514e-06,
+      "loss": 1.9682,
+      "step": 6
+    },
+    {
+      "epoch": 0.02590793430488087,
+      "grad_norm": 16.708574295043945,
+      "learning_rate": 1.4634146341463414e-06,
+      "loss": 2.0057,
+      "step": 7
+    },
+    {
+      "epoch": 0.02960906777700671,
+      "grad_norm": 14.177475929260254,
+      "learning_rate": 1.707317073170732e-06,
+      "loss": 1.9461,
+      "step": 8
+    },
+    {
+      "epoch": 0.033310201249132546,
+      "grad_norm": 12.158246994018555,
+      "learning_rate": 1.951219512195122e-06,
+      "loss": 1.9066,
+      "step": 9
+    },
+    {
+      "epoch": 0.037011334721258386,
+      "grad_norm": 8.045342445373535,
+      "learning_rate": 2.1951219512195125e-06,
+      "loss": 1.8056,
+      "step": 10
+    },
+    {
+      "epoch": 0.04071246819338423,
+      "grad_norm": 7.844163417816162,
+      "learning_rate": 2.4390243902439027e-06,
+      "loss": 1.8378,
+      "step": 11
+    },
+    {
+      "epoch": 0.04441360166551006,
+      "grad_norm": 7.03815221786499,
+      "learning_rate": 2.682926829268293e-06,
+      "loss": 1.8033,
+      "step": 12
+    },
+    {
+      "epoch": 0.0481147351376359,
+      "grad_norm": 3.075176239013672,
+      "learning_rate": 2.926829268292683e-06,
+      "loss": 1.6791,
+      "step": 13
+    },
+    {
+      "epoch": 0.05181586860976174,
+      "grad_norm": 2.8847968578338623,
+      "learning_rate": 3.1707317073170736e-06,
+      "loss": 1.669,
+      "step": 14
+    },
+    {
+      "epoch": 0.055517002081887576,
+      "grad_norm": 2.814876079559326,
+      "learning_rate": 3.414634146341464e-06,
+      "loss": 1.6593,
+      "step": 15
+    },
+    {
+      "epoch": 0.05921813555401342,
+      "grad_norm": 2.5315568447113037,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 1.6243,
+      "step": 16
+    },
+    {
+      "epoch": 0.06291926902613926,
+      "grad_norm": 2.201308488845825,
+      "learning_rate": 3.902439024390244e-06,
+      "loss": 1.635,
+      "step": 17
+    },
+    {
+      "epoch": 0.06662040249826509,
+      "grad_norm": 3.451822280883789,
+      "learning_rate": 4.146341463414634e-06,
+      "loss": 1.5684,
+      "step": 18
+    },
+    {
+      "epoch": 0.07032153597039094,
+      "grad_norm": 3.2633132934570312,
+      "learning_rate": 4.390243902439025e-06,
+      "loss": 1.5289,
+      "step": 19
+    },
+    {
+      "epoch": 0.07402266944251677,
+      "grad_norm": 2.946645736694336,
+      "learning_rate": 4.634146341463416e-06,
+      "loss": 1.5374,
+      "step": 20
+    },
+    {
+      "epoch": 0.0777238029146426,
+      "grad_norm": 2.211390256881714,
+      "learning_rate": 4.8780487804878055e-06,
+      "loss": 1.5406,
+      "step": 21
+    },
+    {
+      "epoch": 0.08142493638676845,
+      "grad_norm": 1.769932746887207,
+      "learning_rate": 5.121951219512195e-06,
+      "loss": 1.5043,
+      "step": 22
+    },
+    {
+      "epoch": 0.08512606985889429,
+      "grad_norm": 1.4464064836502075,
+      "learning_rate": 5.365853658536586e-06,
+      "loss": 1.5019,
+      "step": 23
+    },
+    {
+      "epoch": 0.08882720333102012,
+      "grad_norm": 1.2041360139846802,
+      "learning_rate": 5.609756097560977e-06,
+      "loss": 1.4461,
+      "step": 24
+    },
+    {
+      "epoch": 0.09252833680314597,
+      "grad_norm": 1.348673701286316,
+      "learning_rate": 5.853658536585366e-06,
+      "loss": 1.4275,
+      "step": 25
+    },
+    {
+      "epoch": 0.0962294702752718,
+      "grad_norm": 1.339782476425171,
+      "learning_rate": 6.0975609756097564e-06,
+      "loss": 1.463,
+      "step": 26
+    },
+    {
+      "epoch": 0.09993060374739764,
+      "grad_norm": 1.1694879531860352,
+      "learning_rate": 6.341463414634147e-06,
+      "loss": 1.3685,
+      "step": 27
+    },
+    {
+      "epoch": 0.10363173721952348,
+      "grad_norm": 0.9541494250297546,
+      "learning_rate": 6.585365853658538e-06,
+      "loss": 1.3661,
+      "step": 28
+    },
+    {
+      "epoch": 0.10733287069164932,
+      "grad_norm": 0.7883294224739075,
+      "learning_rate": 6.829268292682928e-06,
+      "loss": 1.3699,
+      "step": 29
+    },
+    {
+      "epoch": 0.11103400416377515,
+      "grad_norm": 0.7608742117881775,
+      "learning_rate": 7.0731707317073175e-06,
+      "loss": 1.3642,
+      "step": 30
+    },
+    {
+      "epoch": 0.114735137635901,
+      "grad_norm": 0.7347314953804016,
+      "learning_rate": 7.317073170731707e-06,
+      "loss": 1.2965,
+      "step": 31
+    },
+    {
+      "epoch": 0.11843627110802683,
+      "grad_norm": 0.7450265288352966,
+      "learning_rate": 7.560975609756098e-06,
+      "loss": 1.334,
+      "step": 32
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 0.7191912531852722,
+      "learning_rate": 7.804878048780489e-06,
+      "loss": 1.3671,
+      "step": 33
+    },
+    {
+      "epoch": 0.12583853805227851,
+      "grad_norm": 0.6597228646278381,
+      "learning_rate": 8.048780487804879e-06,
+      "loss": 1.3567,
+      "step": 34
+    },
+    {
+      "epoch": 0.12953967152440435,
+      "grad_norm": 0.6044723391532898,
+      "learning_rate": 8.292682926829268e-06,
+      "loss": 1.3341,
+      "step": 35
+    },
+    {
+      "epoch": 0.13324080499653018,
+      "grad_norm": 0.608441948890686,
+      "learning_rate": 8.536585365853658e-06,
+      "loss": 1.3191,
+      "step": 36
+    },
+    {
+      "epoch": 0.13694193846865602,
+      "grad_norm": 0.5608295798301697,
+      "learning_rate": 8.78048780487805e-06,
+      "loss": 1.2661,
+      "step": 37
+    },
+    {
+      "epoch": 0.14064307194078188,
+      "grad_norm": 0.524551272392273,
+      "learning_rate": 9.02439024390244e-06,
+      "loss": 1.2925,
+      "step": 38
+    },
+    {
+      "epoch": 0.1443442054129077,
+      "grad_norm": 0.5089970231056213,
+      "learning_rate": 9.268292682926831e-06,
+      "loss": 1.2661,
+      "step": 39
+    },
+    {
+      "epoch": 0.14804533888503354,
+      "grad_norm": 0.5608710050582886,
+      "learning_rate": 9.51219512195122e-06,
+      "loss": 1.3011,
+      "step": 40
+    },
+    {
+      "epoch": 0.15174647235715938,
+      "grad_norm": 0.5306675434112549,
+      "learning_rate": 9.756097560975611e-06,
+      "loss": 1.268,
+      "step": 41
+    },
+    {
+      "epoch": 0.1554476058292852,
+      "grad_norm": 0.5117089152336121,
+      "learning_rate": 1e-05,
+      "loss": 1.2685,
+      "step": 42
+    },
+    {
+      "epoch": 0.15914873930141105,
+      "grad_norm": 0.4487687647342682,
+      "learning_rate": 1.024390243902439e-05,
+      "loss": 1.2687,
+      "step": 43
+    },
+    {
+      "epoch": 0.1628498727735369,
+      "grad_norm": 0.46755310893058777,
+      "learning_rate": 1.0487804878048782e-05,
+      "loss": 1.2394,
+      "step": 44
+    },
+    {
+      "epoch": 0.16655100624566274,
+      "grad_norm": 0.42293983697891235,
+      "learning_rate": 1.0731707317073172e-05,
+      "loss": 1.2567,
+      "step": 45
+    },
+    {
+      "epoch": 0.17025213971778858,
+      "grad_norm": 0.4018270969390869,
+      "learning_rate": 1.0975609756097562e-05,
+      "loss": 1.2472,
+      "step": 46
+    },
+    {
+      "epoch": 0.1739532731899144,
+      "grad_norm": 0.435199499130249,
+      "learning_rate": 1.1219512195121953e-05,
+      "loss": 1.271,
+      "step": 47
+    },
+    {
+      "epoch": 0.17765440666204024,
+      "grad_norm": 0.43060699105262756,
+      "learning_rate": 1.1463414634146342e-05,
+      "loss": 1.271,
+      "step": 48
+    },
+    {
+      "epoch": 0.18135554013416608,
+      "grad_norm": 0.39703771471977234,
+      "learning_rate": 1.1707317073170731e-05,
+      "loss": 1.2637,
+      "step": 49
+    },
+    {
+      "epoch": 0.18505667360629194,
+      "grad_norm": 0.4147438704967499,
+      "learning_rate": 1.1951219512195123e-05,
+      "loss": 1.2618,
+      "step": 50
+    },
+    {
+      "epoch": 0.18875780707841777,
+      "grad_norm": 0.39236122369766235,
+      "learning_rate": 1.2195121951219513e-05,
+      "loss": 1.2319,
+      "step": 51
+    },
+    {
+      "epoch": 0.1924589405505436,
+      "grad_norm": 0.37801605463027954,
+      "learning_rate": 1.2439024390243903e-05,
+      "loss": 1.2331,
+      "step": 52
+    },
+    {
+      "epoch": 0.19616007402266944,
+      "grad_norm": 0.40901511907577515,
+      "learning_rate": 1.2682926829268294e-05,
+      "loss": 1.2287,
+      "step": 53
+    },
+    {
+      "epoch": 0.19986120749479527,
+      "grad_norm": 0.39218148589134216,
+      "learning_rate": 1.2926829268292684e-05,
+      "loss": 1.2329,
+      "step": 54
+    },
+    {
+      "epoch": 0.2035623409669211,
+      "grad_norm": 0.36160245537757874,
+      "learning_rate": 1.3170731707317076e-05,
+      "loss": 1.2418,
+      "step": 55
+    },
+    {
+      "epoch": 0.20726347443904697,
+      "grad_norm": 0.3971434235572815,
+      "learning_rate": 1.3414634146341466e-05,
+      "loss": 1.2105,
+      "step": 56
+    },
+    {
+      "epoch": 0.2109646079111728,
+      "grad_norm": 0.3966448903083801,
+      "learning_rate": 1.3658536585365855e-05,
+      "loss": 1.2237,
+      "step": 57
+    },
+    {
+      "epoch": 0.21466574138329864,
+      "grad_norm": 0.38691452145576477,
+      "learning_rate": 1.3902439024390244e-05,
+      "loss": 1.2103,
+      "step": 58
+    },
+    {
+      "epoch": 0.21836687485542447,
+      "grad_norm": 0.3971393406391144,
+      "learning_rate": 1.4146341463414635e-05,
+      "loss": 1.2076,
+      "step": 59
+    },
+    {
+      "epoch": 0.2220680083275503,
+      "grad_norm": 0.38985714316368103,
+      "learning_rate": 1.4390243902439025e-05,
+      "loss": 1.1594,
+      "step": 60
+    },
+    {
+      "epoch": 0.22576914179967614,
+      "grad_norm": 0.3863939642906189,
+      "learning_rate": 1.4634146341463415e-05,
+      "loss": 1.212,
+      "step": 61
+    },
+    {
+      "epoch": 0.229470275271802,
+      "grad_norm": 0.4149441719055176,
+      "learning_rate": 1.4878048780487806e-05,
+      "loss": 1.2397,
+      "step": 62
+    },
+    {
+      "epoch": 0.23317140874392783,
+      "grad_norm": 0.43418800830841064,
+      "learning_rate": 1.5121951219512196e-05,
+      "loss": 1.2596,
+      "step": 63
+    },
+    {
+      "epoch": 0.23687254221605367,
+      "grad_norm": 0.36480239033699036,
+      "learning_rate": 1.5365853658536586e-05,
+      "loss": 1.2457,
+      "step": 64
+    },
+    {
+      "epoch": 0.2405736756881795,
+      "grad_norm": 0.39555197954177856,
+      "learning_rate": 1.5609756097560978e-05,
+      "loss": 1.1896,
+      "step": 65
+    },
+    {
+      "epoch": 0.24427480916030533,
+      "grad_norm": 0.37620991468429565,
+      "learning_rate": 1.585365853658537e-05,
+      "loss": 1.2087,
+      "step": 66
+    },
+    {
+      "epoch": 0.2479759426324312,
+      "grad_norm": 0.3800138831138611,
+      "learning_rate": 1.6097560975609757e-05,
+      "loss": 1.2376,
+      "step": 67
+    },
+    {
+      "epoch": 0.25167707610455703,
+      "grad_norm": 0.42988261580467224,
+      "learning_rate": 1.6341463414634145e-05,
+      "loss": 1.2025,
+      "step": 68
+    },
+    {
+      "epoch": 0.25537820957668284,
+      "grad_norm": 0.37770283222198486,
+      "learning_rate": 1.6585365853658537e-05,
+      "loss": 1.2234,
+      "step": 69
+    },
+    {
+      "epoch": 0.2590793430488087,
+      "grad_norm": 0.47229480743408203,
+      "learning_rate": 1.682926829268293e-05,
+      "loss": 1.219,
+      "step": 70
+    },
+    {
+      "epoch": 0.26278047652093456,
+      "grad_norm": 0.4039227068424225,
+      "learning_rate": 1.7073170731707317e-05,
+      "loss": 1.1951,
+      "step": 71
+    },
+    {
+      "epoch": 0.26648160999306036,
+      "grad_norm": 0.45078909397125244,
+      "learning_rate": 1.7317073170731708e-05,
+      "loss": 1.1876,
+      "step": 72
+    },
+    {
+      "epoch": 0.2701827434651862,
+      "grad_norm": 0.41969749331474304,
+      "learning_rate": 1.75609756097561e-05,
+      "loss": 1.1933,
+      "step": 73
+    },
+    {
+      "epoch": 0.27388387693731203,
+      "grad_norm": 0.43968865275382996,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 1.206,
+      "step": 74
+    },
+    {
+      "epoch": 0.2775850104094379,
+      "grad_norm": 0.4713888466358185,
+      "learning_rate": 1.804878048780488e-05,
+      "loss": 1.2222,
+      "step": 75
+    },
+    {
+      "epoch": 0.28128614388156375,
+      "grad_norm": 0.4152630865573883,
+      "learning_rate": 1.829268292682927e-05,
+      "loss": 1.1792,
+      "step": 76
+    },
+    {
+      "epoch": 0.28498727735368956,
+      "grad_norm": 0.43539732694625854,
+      "learning_rate": 1.8536585365853663e-05,
+      "loss": 1.1674,
+      "step": 77
+    },
+    {
+      "epoch": 0.2886884108258154,
+      "grad_norm": 0.427062451839447,
+      "learning_rate": 1.878048780487805e-05,
+      "loss": 1.1972,
+      "step": 78
+    },
+    {
+      "epoch": 0.29238954429794123,
+      "grad_norm": 0.4538004696369171,
+      "learning_rate": 1.902439024390244e-05,
+      "loss": 1.174,
+      "step": 79
+    },
+    {
+      "epoch": 0.2960906777700671,
+      "grad_norm": 0.4255438446998596,
+      "learning_rate": 1.926829268292683e-05,
+      "loss": 1.1903,
+      "step": 80
+    },
+    {
+      "epoch": 0.2997918112421929,
+      "grad_norm": 0.44163715839385986,
+      "learning_rate": 1.9512195121951222e-05,
+      "loss": 1.1961,
+      "step": 81
+    },
+    {
+      "epoch": 0.30349294471431876,
+      "grad_norm": 0.47783321142196655,
+      "learning_rate": 1.975609756097561e-05,
+      "loss": 1.1797,
+      "step": 82
+    },
+    {
+      "epoch": 0.3071940781864446,
+      "grad_norm": 0.524274468421936,
+      "learning_rate": 2e-05,
+      "loss": 1.2058,
+      "step": 83
+    },
+    {
+      "epoch": 0.3108952116585704,
+      "grad_norm": 0.43504446744918823,
+      "learning_rate": 1.9999907650547006e-05,
+      "loss": 1.1561,
+      "step": 84
+    },
+    {
+      "epoch": 0.3145963451306963,
+      "grad_norm": 0.5196582674980164,
+      "learning_rate": 1.999963060389371e-05,
+      "loss": 1.2008,
+      "step": 85
+    },
+    {
+      "epoch": 0.3182974786028221,
+      "grad_norm": 0.48404446244239807,
+      "learning_rate": 1.9999168865157137e-05,
+      "loss": 1.1837,
+      "step": 86
+    },
+    {
+      "epoch": 0.32199861207494795,
+      "grad_norm": 0.5402565598487854,
+      "learning_rate": 1.999852244286554e-05,
+      "loss": 1.1739,
+      "step": 87
+    },
+    {
+      "epoch": 0.3256997455470738,
+      "grad_norm": 0.45610666275024414,
+      "learning_rate": 1.9997691348958278e-05,
+      "loss": 1.2023,
+      "step": 88
+    },
+    {
+      "epoch": 0.3294008790191996,
+      "grad_norm": 0.5024977922439575,
+      "learning_rate": 1.999667559878556e-05,
+      "loss": 1.2208,
+      "step": 89
+    },
+    {
+      "epoch": 0.3331020124913255,
+      "grad_norm": 0.47227853536605835,
+      "learning_rate": 1.9995475211108183e-05,
+      "loss": 1.1853,
+      "step": 90
+    },
+    {
+      "epoch": 0.3368031459634513,
+      "grad_norm": 0.47440260648727417,
+      "learning_rate": 1.9994090208097176e-05,
+      "loss": 1.1841,
+      "step": 91
+    },
+    {
+      "epoch": 0.34050427943557715,
+      "grad_norm": 0.4835188090801239,
+      "learning_rate": 1.9992520615333393e-05,
+      "loss": 1.2107,
+      "step": 92
+    },
+    {
+      "epoch": 0.34420541290770296,
+      "grad_norm": 0.4680016338825226,
+      "learning_rate": 1.9990766461807037e-05,
+      "loss": 1.165,
+      "step": 93
+    },
+    {
+      "epoch": 0.3479065463798288,
+      "grad_norm": 0.4826832115650177,
+      "learning_rate": 1.9988827779917138e-05,
+      "loss": 1.153,
+      "step": 94
+    },
+    {
+      "epoch": 0.3516076798519547,
+      "grad_norm": 0.4597121775150299,
+      "learning_rate": 1.9986704605470932e-05,
+      "loss": 1.1786,
+      "step": 95
+    },
+    {
+      "epoch": 0.3553088133240805,
+      "grad_norm": 0.4732728898525238,
+      "learning_rate": 1.9984396977683223e-05,
+      "loss": 1.2066,
+      "step": 96
+    },
+    {
+      "epoch": 0.35900994679620635,
+      "grad_norm": 0.5414657592773438,
+      "learning_rate": 1.998190493917564e-05,
+      "loss": 1.1748,
+      "step": 97
+    },
+    {
+      "epoch": 0.36271108026833215,
+      "grad_norm": 0.46830272674560547,
+      "learning_rate": 1.9979228535975866e-05,
+      "loss": 1.159,
+      "step": 98
+    },
+    {
+      "epoch": 0.366412213740458,
+      "grad_norm": 0.4553397297859192,
+      "learning_rate": 1.9976367817516773e-05,
+      "loss": 1.1862,
+      "step": 99
+    },
+    {
+      "epoch": 0.3701133472125839,
+      "grad_norm": 0.4947619140148163,
+      "learning_rate": 1.9973322836635517e-05,
+      "loss": 1.172,
+      "step": 100
+    },
+    {
+      "epoch": 0.3738144806847097,
+      "grad_norm": 0.4160066246986389,
+      "learning_rate": 1.9970093649572567e-05,
+      "loss": 1.174,
+      "step": 101
+    },
+    {
+      "epoch": 0.37751561415683554,
+      "grad_norm": 0.44229212403297424,
+      "learning_rate": 1.9966680315970647e-05,
+      "loss": 1.1987,
+      "step": 102
+    },
+    {
+      "epoch": 0.38121674762896135,
+      "grad_norm": 0.4374721944332123,
+      "learning_rate": 1.996308289887366e-05,
+      "loss": 1.1773,
+      "step": 103
+    },
+    {
+      "epoch": 0.3849178811010872,
+      "grad_norm": 0.45597878098487854,
+      "learning_rate": 1.9959301464725507e-05,
+      "loss": 1.1696,
+      "step": 104
+    },
+    {
+      "epoch": 0.3886190145732131,
+      "grad_norm": 0.43197211623191833,
+      "learning_rate": 1.995533608336886e-05,
+      "loss": 1.1528,
+      "step": 105
+    },
+    {
+      "epoch": 0.3923201480453389,
+      "grad_norm": 0.4520713686943054,
+      "learning_rate": 1.995118682804388e-05,
+      "loss": 1.1522,
+      "step": 106
+    },
+    {
+      "epoch": 0.39602128151746474,
+      "grad_norm": 0.4522034525871277,
+      "learning_rate": 1.9946853775386857e-05,
+      "loss": 1.1657,
+      "step": 107
+    },
+    {
+      "epoch": 0.39972241498959055,
+      "grad_norm": 0.5125685930252075,
+      "learning_rate": 1.9942337005428805e-05,
+      "loss": 1.1875,
+      "step": 108
+    },
+    {
+      "epoch": 0.4034235484617164,
+      "grad_norm": 0.43560755252838135,
+      "learning_rate": 1.9937636601593965e-05,
+      "loss": 1.1501,
+      "step": 109
+    },
+    {
+      "epoch": 0.4071246819338422,
+      "grad_norm": 0.44878366589546204,
+      "learning_rate": 1.9932752650698285e-05,
+      "loss": 1.1649,
+      "step": 110
+    },
+    {
+      "epoch": 0.4108258154059681,
+      "grad_norm": 0.4889513850212097,
+      "learning_rate": 1.9927685242947804e-05,
+      "loss": 1.1736,
+      "step": 111
+    },
+    {
+      "epoch": 0.41452694887809394,
+      "grad_norm": 0.42187580466270447,
+      "learning_rate": 1.9922434471936987e-05,
+      "loss": 1.1463,
+      "step": 112
+    },
+    {
+      "epoch": 0.41822808235021974,
+      "grad_norm": 0.435621976852417,
+      "learning_rate": 1.9917000434647e-05,
+      "loss": 1.1582,
+      "step": 113
+    },
+    {
+      "epoch": 0.4219292158223456,
+      "grad_norm": 0.47740185260772705,
+      "learning_rate": 1.991138323144392e-05,
+      "loss": 1.1585,
+      "step": 114
+    },
+    {
+      "epoch": 0.4256303492944714,
+      "grad_norm": 0.44095510244369507,
+      "learning_rate": 1.990558296607687e-05,
+      "loss": 1.1787,
+      "step": 115
+    },
+    {
+      "epoch": 0.42933148276659727,
+      "grad_norm": 0.44858500361442566,
+      "learning_rate": 1.9899599745676123e-05,
+      "loss": 1.1428,
+      "step": 116
+    },
+    {
+      "epoch": 0.43303261623872313,
+      "grad_norm": 0.4960203766822815,
+      "learning_rate": 1.9893433680751105e-05,
+      "loss": 1.174,
+      "step": 117
+    },
+    {
+      "epoch": 0.43673374971084894,
+      "grad_norm": 0.45929455757141113,
+      "learning_rate": 1.9887084885188354e-05,
+      "loss": 1.1903,
+      "step": 118
+    },
+    {
+      "epoch": 0.4404348831829748,
+      "grad_norm": 0.4894520342350006,
+      "learning_rate": 1.9880553476249437e-05,
+      "loss": 1.1517,
+      "step": 119
+    },
+    {
+      "epoch": 0.4441360166551006,
+      "grad_norm": 0.4524790048599243,
+      "learning_rate": 1.9873839574568756e-05,
+      "loss": 1.1215,
+      "step": 120
+    },
+    {
+      "epoch": 0.44783715012722647,
+      "grad_norm": 0.446846067905426,
+      "learning_rate": 1.9866943304151346e-05,
+      "loss": 1.1471,
+      "step": 121
+    },
+    {
+      "epoch": 0.4515382835993523,
+      "grad_norm": 0.43665164709091187,
+      "learning_rate": 1.9859864792370565e-05,
+      "loss": 1.1369,
+      "step": 122
+    },
+    {
+      "epoch": 0.45523941707147814,
+      "grad_norm": 0.45532330870628357,
+      "learning_rate": 1.985260416996575e-05,
+      "loss": 1.1714,
+      "step": 123
+    },
+    {
+      "epoch": 0.458940550543604,
+      "grad_norm": 0.5525180101394653,
+      "learning_rate": 1.9845161571039805e-05,
+      "loss": 1.1394,
+      "step": 124
+    },
+    {
+      "epoch": 0.4626416840157298,
+      "grad_norm": 0.5021325349807739,
+      "learning_rate": 1.983753713305672e-05,
+      "loss": 1.1804,
+      "step": 125
+    },
+    {
+      "epoch": 0.46634281748785567,
+      "grad_norm": 0.45662885904312134,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 1.1423,
+      "step": 126
+    },
+    {
+      "epoch": 0.47004395095998147,
+      "grad_norm": 0.489346444606781,
+      "learning_rate": 1.98217433065652e-05,
+      "loss": 1.1544,
+      "step": 127
+    },
+    {
+      "epoch": 0.47374508443210733,
+      "grad_norm": 0.5123556852340698,
+      "learning_rate": 1.9813574209767013e-05,
+      "loss": 1.1704,
+      "step": 128
+    },
+    {
+      "epoch": 0.4774462179042332,
+      "grad_norm": 0.4498573839664459,
+      "learning_rate": 1.9805223857326794e-05,
+      "loss": 1.1672,
+      "step": 129
+    },
+    {
+      "epoch": 0.481147351376359,
+      "grad_norm": 0.5040275454521179,
+      "learning_rate": 1.9796692403474632e-05,
+      "loss": 1.1436,
+      "step": 130
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.48043787479400635,
+      "learning_rate": 1.9787980005785553e-05,
+      "loss": 1.1744,
+      "step": 131
+    },
+    {
+      "epoch": 0.48854961832061067,
+      "grad_norm": 0.5542130470275879,
+      "learning_rate": 1.977908682517658e-05,
+      "loss": 1.1403,
+      "step": 132
+    },
+    {
+      "epoch": 0.49225075179273653,
+      "grad_norm": 0.4555543065071106,
+      "learning_rate": 1.9770013025903797e-05,
+      "loss": 1.1437,
+      "step": 133
+    },
+    {
+      "epoch": 0.4959518852648624,
+      "grad_norm": 0.4997326135635376,
+      "learning_rate": 1.9760758775559275e-05,
+      "loss": 1.1239,
+      "step": 134
+    },
+    {
+      "epoch": 0.4996530187369882,
+      "grad_norm": 0.470058798789978,
+      "learning_rate": 1.9751324245068008e-05,
+      "loss": 1.1752,
+      "step": 135
+    },
+    {
+      "epoch": 0.5033541522091141,
+      "grad_norm": 0.47833555936813354,
+      "learning_rate": 1.974170960868474e-05,
+      "loss": 1.1652,
+      "step": 136
+    },
+    {
+      "epoch": 0.5070552856812399,
+      "grad_norm": 0.46740809082984924,
+      "learning_rate": 1.973191504399076e-05,
+      "loss": 1.1243,
+      "step": 137
+    },
+    {
+      "epoch": 0.5107564191533657,
+      "grad_norm": 0.4260287582874298,
+      "learning_rate": 1.97219407318906e-05,
+      "loss": 1.1457,
+      "step": 138
+    },
+    {
+      "epoch": 0.5144575526254915,
+      "grad_norm": 0.4864775538444519,
+      "learning_rate": 1.9711786856608714e-05,
+      "loss": 1.1405,
+      "step": 139
+    },
+    {
+      "epoch": 0.5181586860976174,
+      "grad_norm": 0.4291229844093323,
+      "learning_rate": 1.970145360568607e-05,
+      "loss": 1.1906,
+      "step": 140
+    },
+    {
+      "epoch": 0.5218598195697433,
+      "grad_norm": 0.5193659663200378,
+      "learning_rate": 1.969094116997668e-05,
+      "loss": 1.1328,
+      "step": 141
+    },
+    {
+      "epoch": 0.5255609530418691,
+      "grad_norm": 0.4072008430957794,
+      "learning_rate": 1.968024974364408e-05,
+      "loss": 1.1891,
+      "step": 142
+    },
+    {
+      "epoch": 0.5292620865139949,
+      "grad_norm": 0.49957630038261414,
+      "learning_rate": 1.9669379524157755e-05,
+      "loss": 1.1667,
+      "step": 143
+    },
+    {
+      "epoch": 0.5329632199861207,
+      "grad_norm": 0.46822240948677063,
+      "learning_rate": 1.9658330712289456e-05,
+      "loss": 1.1416,
+      "step": 144
+    },
+    {
+      "epoch": 0.5366643534582466,
+      "grad_norm": 0.44118058681488037,
+      "learning_rate": 1.9647103512109535e-05,
+      "loss": 1.142,
+      "step": 145
+    },
+    {
+      "epoch": 0.5403654869303725,
+      "grad_norm": 0.46672412753105164,
+      "learning_rate": 1.9635698130983153e-05,
+      "loss": 1.1702,
+      "step": 146
+    },
+    {
+      "epoch": 0.5440666204024983,
+      "grad_norm": 0.4547111690044403,
+      "learning_rate": 1.962411477956645e-05,
+      "loss": 1.1495,
+      "step": 147
+    },
+    {
+      "epoch": 0.5477677538746241,
+      "grad_norm": 0.4423418343067169,
+      "learning_rate": 1.9612353671802658e-05,
+      "loss": 1.128,
+      "step": 148
+    },
+    {
+      "epoch": 0.5514688873467499,
+      "grad_norm": 0.49529922008514404,
+      "learning_rate": 1.960041502491815e-05,
+      "loss": 1.1488,
+      "step": 149
+    },
+    {
+      "epoch": 0.5551700208188758,
+      "grad_norm": 0.4977218210697174,
+      "learning_rate": 1.9588299059418434e-05,
+      "loss": 1.1268,
+      "step": 150
+    },
+    {
+      "epoch": 0.5588711542910016,
+      "grad_norm": 0.5749414563179016,
+      "learning_rate": 1.957600599908406e-05,
+      "loss": 1.1438,
+      "step": 151
+    },
+    {
+      "epoch": 0.5625722877631275,
+      "grad_norm": 0.4806205630302429,
+      "learning_rate": 1.9563536070966513e-05,
+      "loss": 1.1278,
+      "step": 152
+    },
+    {
+      "epoch": 0.5662734212352533,
+      "grad_norm": 0.5104363560676575,
+      "learning_rate": 1.9550889505383996e-05,
+      "loss": 1.1182,
+      "step": 153
+    },
+    {
+      "epoch": 0.5699745547073791,
+      "grad_norm": 0.4537147879600525,
+      "learning_rate": 1.9538066535917196e-05,
+      "loss": 1.1617,
+      "step": 154
+    },
+    {
+      "epoch": 0.573675688179505,
+      "grad_norm": 0.5351677536964417,
+      "learning_rate": 1.952506739940496e-05,
+      "loss": 1.1388,
+      "step": 155
+    },
+    {
+      "epoch": 0.5773768216516308,
+      "grad_norm": 0.4276635944843292,
+      "learning_rate": 1.9511892335939904e-05,
+      "loss": 1.1267,
+      "step": 156
+    },
+    {
+      "epoch": 0.5810779551237566,
+      "grad_norm": 0.5219061374664307,
+      "learning_rate": 1.9498541588864022e-05,
+      "loss": 1.1646,
+      "step": 157
+    },
+    {
+      "epoch": 0.5847790885958825,
+      "grad_norm": 0.6277289986610413,
+      "learning_rate": 1.948501540476414e-05,
+      "loss": 1.1527,
+      "step": 158
+    },
+    {
+      "epoch": 0.5884802220680083,
+      "grad_norm": 0.4811258614063263,
+      "learning_rate": 1.9471314033467413e-05,
+      "loss": 1.167,
+      "step": 159
+    },
+    {
+      "epoch": 0.5921813555401342,
+      "grad_norm": 0.45152518153190613,
+      "learning_rate": 1.945743772803666e-05,
+      "loss": 1.1623,
+      "step": 160
+    },
+    {
+      "epoch": 0.59588248901226,
+      "grad_norm": 0.4437843859195709,
+      "learning_rate": 1.9443386744765726e-05,
+      "loss": 1.1692,
+      "step": 161
+    },
+    {
+      "epoch": 0.5995836224843858,
+      "grad_norm": 0.43210992217063904,
+      "learning_rate": 1.942916134317473e-05,
+      "loss": 1.1692,
+      "step": 162
+    },
+    {
+      "epoch": 0.6032847559565117,
+      "grad_norm": 0.4339381456375122,
+      "learning_rate": 1.9414761786005293e-05,
+      "loss": 1.1394,
+      "step": 163
+    },
+    {
+      "epoch": 0.6069858894286375,
+      "grad_norm": 0.44703447818756104,
+      "learning_rate": 1.9400188339215657e-05,
+      "loss": 1.1581,
+      "step": 164
+    },
+    {
+      "epoch": 0.6106870229007634,
+      "grad_norm": 0.48046809434890747,
+      "learning_rate": 1.9385441271975786e-05,
+      "loss": 1.104,
+      "step": 165
+    },
+    {
+      "epoch": 0.6143881563728892,
+      "grad_norm": 0.45704057812690735,
+      "learning_rate": 1.9370520856662406e-05,
+      "loss": 1.1412,
+      "step": 166
+    },
+    {
+      "epoch": 0.618089289845015,
+      "grad_norm": 0.49565792083740234,
+      "learning_rate": 1.9355427368853946e-05,
+      "loss": 1.1873,
+      "step": 167
+    },
+    {
+      "epoch": 0.6217904233171409,
+      "grad_norm": 0.49605411291122437,
+      "learning_rate": 1.9340161087325483e-05,
+      "loss": 1.1419,
+      "step": 168
+    },
+    {
+      "epoch": 0.6254915567892667,
+      "grad_norm": 0.41736945509910583,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 1.1198,
+      "step": 169
+    },
+    {
+      "epoch": 0.6291926902613926,
+      "grad_norm": 0.4974633753299713,
+      "learning_rate": 1.9309111274161005e-05,
+      "loss": 1.173,
+      "step": 170
+    },
+    {
+      "epoch": 0.6328938237335184,
+      "grad_norm": 0.4752466678619385,
+      "learning_rate": 1.9293328316011645e-05,
+      "loss": 1.1442,
+      "step": 171
+    },
+    {
+      "epoch": 0.6365949572056442,
+      "grad_norm": 0.44637349247932434,
+      "learning_rate": 1.927737371110499e-05,
+      "loss": 1.1357,
+      "step": 172
+    },
+    {
+      "epoch": 0.64029609067777,
+      "grad_norm": 0.5463848114013672,
+      "learning_rate": 1.9261247754120846e-05,
+      "loss": 1.1143,
+      "step": 173
+    },
+    {
+      "epoch": 0.6439972241498959,
+      "grad_norm": 0.43191689252853394,
+      "learning_rate": 1.924495074290388e-05,
+      "loss": 1.1357,
+      "step": 174
+    },
+    {
+      "epoch": 0.6476983576220218,
+      "grad_norm": 0.5463783740997314,
+      "learning_rate": 1.92284829784581e-05,
+      "loss": 1.1117,
+      "step": 175
+    },
+    {
+      "epoch": 0.6513994910941476,
+      "grad_norm": 0.5015990734100342,
+      "learning_rate": 1.9211844764941318e-05,
+      "loss": 1.1405,
+      "step": 176
+    },
+    {
+      "epoch": 0.6551006245662734,
+      "grad_norm": 0.492009699344635,
+      "learning_rate": 1.919503640965951e-05,
+      "loss": 1.1621,
+      "step": 177
+    },
+    {
+      "epoch": 0.6588017580383992,
+      "grad_norm": 0.529156506061554,
+      "learning_rate": 1.917805822306117e-05,
+      "loss": 1.1778,
+      "step": 178
+    },
+    {
+      "epoch": 0.6625028915105251,
+      "grad_norm": 0.4173935353755951,
+      "learning_rate": 1.916091051873154e-05,
+      "loss": 1.1142,
+      "step": 179
+    },
+    {
+      "epoch": 0.666204024982651,
+      "grad_norm": 0.4969713091850281,
+      "learning_rate": 1.9143593613386845e-05,
+      "loss": 1.1195,
+      "step": 180
+    },
+    {
+      "epoch": 0.6699051584547768,
+      "grad_norm": 0.5533036589622498,
+      "learning_rate": 1.9126107826868436e-05,
+      "loss": 1.1436,
+      "step": 181
+    },
+    {
+      "epoch": 0.6736062919269026,
+      "grad_norm": 0.5528081059455872,
+      "learning_rate": 1.9108453482136866e-05,
+      "loss": 1.1738,
+      "step": 182
+    },
+    {
+      "epoch": 0.6773074253990284,
+      "grad_norm": 0.4741283357143402,
+      "learning_rate": 1.9090630905265963e-05,
+      "loss": 1.1766,
+      "step": 183
+    },
+    {
+      "epoch": 0.6810085588711543,
+      "grad_norm": 0.5676066279411316,
+      "learning_rate": 1.9072640425436762e-05,
+      "loss": 1.1437,
+      "step": 184
+    },
+    {
+      "epoch": 0.6847096923432802,
+      "grad_norm": 0.4501611292362213,
+      "learning_rate": 1.905448237493147e-05,
+      "loss": 1.1434,
+      "step": 185
+    },
+    {
+      "epoch": 0.6884108258154059,
+      "grad_norm": 0.542989194393158,
+      "learning_rate": 1.9036157089127278e-05,
+      "loss": 1.1482,
+      "step": 186
+    },
+    {
+      "epoch": 0.6921119592875318,
+      "grad_norm": 0.5076568126678467,
+      "learning_rate": 1.901766490649022e-05,
+      "loss": 1.1319,
+      "step": 187
+    },
+    {
+      "epoch": 0.6958130927596576,
+      "grad_norm": 0.5173127055168152,
+      "learning_rate": 1.8999006168568883e-05,
+      "loss": 1.1485,
+      "step": 188
+    },
+    {
+      "epoch": 0.6995142262317835,
+      "grad_norm": 0.517465353012085,
+      "learning_rate": 1.8980181219988117e-05,
+      "loss": 1.1349,
+      "step": 189
+    },
+    {
+      "epoch": 0.7032153597039094,
+      "grad_norm": 0.4963802397251129,
+      "learning_rate": 1.8961190408442662e-05,
+      "loss": 1.1336,
+      "step": 190
+    },
+    {
+      "epoch": 0.7069164931760351,
+      "grad_norm": 0.4494330883026123,
+      "learning_rate": 1.8942034084690727e-05,
+      "loss": 1.1215,
+      "step": 191
+    },
+    {
+      "epoch": 0.710617626648161,
+      "grad_norm": 0.49428790807724,
+      "learning_rate": 1.8922712602547516e-05,
+      "loss": 1.1203,
+      "step": 192
+    },
+    {
+      "epoch": 0.7143187601202868,
+      "grad_norm": 0.43069377541542053,
+      "learning_rate": 1.89032263188787e-05,
+      "loss": 1.1058,
+      "step": 193
+    },
+    {
+      "epoch": 0.7180198935924127,
+      "grad_norm": 0.4609989523887634,
+      "learning_rate": 1.8883575593593793e-05,
+      "loss": 1.112,
+      "step": 194
+    },
+    {
+      "epoch": 0.7217210270645386,
+      "grad_norm": 0.43700459599494934,
+      "learning_rate": 1.8863760789639548e-05,
+      "loss": 1.1566,
+      "step": 195
+    },
+    {
+      "epoch": 0.7254221605366643,
+      "grad_norm": 0.480736643075943,
+      "learning_rate": 1.8843782272993225e-05,
+      "loss": 1.1499,
+      "step": 196
+    },
+    {
+      "epoch": 0.7291232940087902,
+      "grad_norm": 0.4634736180305481,
+      "learning_rate": 1.8823640412655844e-05,
+      "loss": 1.0988,
+      "step": 197
+    },
+    {
+      "epoch": 0.732824427480916,
+      "grad_norm": 0.4300520420074463,
+      "learning_rate": 1.880333558064536e-05,
+      "loss": 1.1141,
+      "step": 198
+    },
+    {
+      "epoch": 0.7365255609530419,
+      "grad_norm": 0.4690033793449402,
+      "learning_rate": 1.878286815198979e-05,
+      "loss": 1.1454,
+      "step": 199
+    },
+    {
+      "epoch": 0.7402266944251678,
+      "grad_norm": 0.40673312544822693,
+      "learning_rate": 1.876223850472032e-05,
+      "loss": 1.1273,
+      "step": 200
+    },
+    {
+      "epoch": 0.7439278278972935,
+      "grad_norm": 0.4603167474269867,
+      "learning_rate": 1.8741447019864263e-05,
+      "loss": 1.1334,
+      "step": 201
+    },
+    {
+      "epoch": 0.7476289613694194,
+      "grad_norm": 0.4728105068206787,
+      "learning_rate": 1.872049408143808e-05,
+      "loss": 1.1185,
+      "step": 202
+    },
+    {
+      "epoch": 0.7513300948415452,
+      "grad_norm": 0.47324028611183167,
+      "learning_rate": 1.8699380076440242e-05,
+      "loss": 1.1362,
+      "step": 203
+    },
+    {
+      "epoch": 0.7550312283136711,
+      "grad_norm": 0.4205387532711029,
+      "learning_rate": 1.8678105394844114e-05,
+      "loss": 1.1291,
+      "step": 204
+    },
+    {
+      "epoch": 0.758732361785797,
+      "grad_norm": 0.4776360094547272,
+      "learning_rate": 1.8656670429590745e-05,
+      "loss": 1.1372,
+      "step": 205
+    },
+    {
+      "epoch": 0.7624334952579227,
+      "grad_norm": 0.4702264964580536,
+      "learning_rate": 1.8635075576581587e-05,
+      "loss": 1.1183,
+      "step": 206
+    },
+    {
+      "epoch": 0.7661346287300486,
+      "grad_norm": 0.39752131700515747,
+      "learning_rate": 1.861332123467122e-05,
+      "loss": 1.1463,
+      "step": 207
+    },
+    {
+      "epoch": 0.7698357622021744,
+      "grad_norm": 0.5406947731971741,
+      "learning_rate": 1.859140780565996e-05,
+      "loss": 1.1443,
+      "step": 208
+    },
+    {
+      "epoch": 0.7735368956743003,
+      "grad_norm": 0.3916800320148468,
+      "learning_rate": 1.856933569428644e-05,
+      "loss": 1.1318,
+      "step": 209
+    },
+    {
+      "epoch": 0.7772380291464261,
+      "grad_norm": 0.4341064989566803,
+      "learning_rate": 1.8547105308220142e-05,
+      "loss": 1.119,
+      "step": 210
+    },
+    {
+      "epoch": 0.7809391626185519,
+      "grad_norm": 0.4670443534851074,
+      "learning_rate": 1.852471705805387e-05,
+      "loss": 1.1254,
+      "step": 211
+    },
+    {
+      "epoch": 0.7846402960906778,
+      "grad_norm": 0.4435541331768036,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 1.1543,
+      "step": 212
+    },
+    {
+      "epoch": 0.7883414295628036,
+      "grad_norm": 0.4735044836997986,
+      "learning_rate": 1.84794686223636e-05,
+      "loss": 1.1309,
+      "step": 213
+    },
+    {
+      "epoch": 0.7920425630349295,
+      "grad_norm": 0.49449247121810913,
+      "learning_rate": 1.8456609272573268e-05,
+      "loss": 1.1602,
+      "step": 214
+    },
+    {
+      "epoch": 0.7957436965070552,
+      "grad_norm": 0.46075525879859924,
+      "learning_rate": 1.8433593730134835e-05,
+      "loss": 1.1084,
+      "step": 215
+    },
+    {
+      "epoch": 0.7994448299791811,
+      "grad_norm": 0.49750804901123047,
+      "learning_rate": 1.841042242014285e-05,
+      "loss": 1.1639,
+      "step": 216
+    },
+    {
+      "epoch": 0.803145963451307,
+      "grad_norm": 0.46192413568496704,
+      "learning_rate": 1.838709577056888e-05,
+      "loss": 1.1041,
+      "step": 217
+    },
+    {
+      "epoch": 0.8068470969234328,
+      "grad_norm": 0.47443869709968567,
+      "learning_rate": 1.8363614212253585e-05,
+      "loss": 1.1089,
+      "step": 218
+    },
+    {
+      "epoch": 0.8105482303955587,
+      "grad_norm": 0.4756864309310913,
+      "learning_rate": 1.833997817889878e-05,
+      "loss": 1.105,
+      "step": 219
+    },
+    {
+      "epoch": 0.8142493638676844,
+      "grad_norm": 0.43266934156417847,
+      "learning_rate": 1.8316188107059418e-05,
+      "loss": 1.1341,
+      "step": 220
+    },
+    {
+      "epoch": 0.8179504973398103,
+      "grad_norm": 0.504323422908783,
+      "learning_rate": 1.8292244436135517e-05,
+      "loss": 1.1365,
+      "step": 221
+    },
+    {
+      "epoch": 0.8216516308119362,
+      "grad_norm": 0.4178315997123718,
+      "learning_rate": 1.8268147608364068e-05,
+      "loss": 1.126,
+      "step": 222
+    },
+    {
+      "epoch": 0.825352764284062,
+      "grad_norm": 0.4512770175933838,
+      "learning_rate": 1.8243898068810833e-05,
+      "loss": 1.0825,
+      "step": 223
+    },
+    {
+      "epoch": 0.8290538977561879,
+      "grad_norm": 0.4697542190551758,
+      "learning_rate": 1.8219496265362164e-05,
+      "loss": 1.0932,
+      "step": 224
+    },
+    {
+      "epoch": 0.8327550312283136,
+      "grad_norm": 0.4374232590198517,
+      "learning_rate": 1.81949426487167e-05,
+      "loss": 1.1341,
+      "step": 225
+    },
+    {
+      "epoch": 0.8364561647004395,
+      "grad_norm": 0.41643136739730835,
+      "learning_rate": 1.8170237672377046e-05,
+      "loss": 1.1146,
+      "step": 226
+    },
+    {
+      "epoch": 0.8401572981725653,
+      "grad_norm": 0.45138299465179443,
+      "learning_rate": 1.814538179264142e-05,
+      "loss": 1.1147,
+      "step": 227
+    },
+    {
+      "epoch": 0.8438584316446912,
+      "grad_norm": 0.4233904778957367,
+      "learning_rate": 1.81203754685952e-05,
+      "loss": 1.1297,
+      "step": 228
+    },
+    {
+      "epoch": 0.8475595651168171,
+      "grad_norm": 0.5106139183044434,
+      "learning_rate": 1.8095219162102453e-05,
+      "loss": 1.1147,
+      "step": 229
+    },
+    {
+      "epoch": 0.8512606985889428,
+      "grad_norm": 0.44398224353790283,
+      "learning_rate": 1.8069913337797414e-05,
+      "loss": 1.1274,
+      "step": 230
+    },
+    {
+      "epoch": 0.8549618320610687,
+      "grad_norm": 0.506275475025177,
+      "learning_rate": 1.804445846307588e-05,
+      "loss": 1.1383,
+      "step": 231
+    },
+    {
+      "epoch": 0.8586629655331945,
+      "grad_norm": 0.46077436208724976,
+      "learning_rate": 1.801885500808661e-05,
+      "loss": 1.0964,
+      "step": 232
+    },
+    {
+      "epoch": 0.8623640990053204,
+      "grad_norm": 0.5077394843101501,
+      "learning_rate": 1.7993103445722615e-05,
+      "loss": 1.131,
+      "step": 233
+    },
+    {
+      "epoch": 0.8660652324774463,
+      "grad_norm": 0.48133185505867004,
+      "learning_rate": 1.7967204251612432e-05,
+      "loss": 1.1366,
+      "step": 234
+    },
+    {
+      "epoch": 0.869766365949572,
+      "grad_norm": 0.4848846197128296,
+      "learning_rate": 1.7941157904111346e-05,
+      "loss": 1.1426,
+      "step": 235
+    },
+    {
+      "epoch": 0.8734674994216979,
+      "grad_norm": 0.5075129866600037,
+      "learning_rate": 1.7914964884292543e-05,
+      "loss": 1.1,
+      "step": 236
+    },
+    {
+      "epoch": 0.8771686328938237,
+      "grad_norm": 0.43443480134010315,
+      "learning_rate": 1.7888625675938237e-05,
+      "loss": 1.1435,
+      "step": 237
+    },
+    {
+      "epoch": 0.8808697663659496,
+      "grad_norm": 0.567414402961731,
+      "learning_rate": 1.7862140765530718e-05,
+      "loss": 1.0904,
+      "step": 238
+    },
+    {
+      "epoch": 0.8845708998380755,
+      "grad_norm": 0.5032252073287964,
+      "learning_rate": 1.783551064224339e-05,
+      "loss": 1.1429,
+      "step": 239
+    },
+    {
+      "epoch": 0.8882720333102012,
+      "grad_norm": 0.461820513010025,
+      "learning_rate": 1.7808735797931715e-05,
+      "loss": 1.1108,
+      "step": 240
+    },
+    {
+      "epoch": 0.8919731667823271,
+      "grad_norm": 0.4861697852611542,
+      "learning_rate": 1.7781816727124138e-05,
+      "loss": 1.0938,
+      "step": 241
+    },
+    {
+      "epoch": 0.8956743002544529,
+      "grad_norm": 0.5366714000701904,
+      "learning_rate": 1.7754753927012955e-05,
+      "loss": 1.1144,
+      "step": 242
+    },
+    {
+      "epoch": 0.8993754337265788,
+      "grad_norm": 0.4563060700893402,
+      "learning_rate": 1.7727547897445117e-05,
+      "loss": 1.1164,
+      "step": 243
+    },
+    {
+      "epoch": 0.9030765671987045,
+      "grad_norm": 0.5184001922607422,
+      "learning_rate": 1.770019914091302e-05,
+      "loss": 1.1357,
+      "step": 244
+    },
+    {
+      "epoch": 0.9067777006708304,
+      "grad_norm": 0.44209641218185425,
+      "learning_rate": 1.76727081625452e-05,
+      "loss": 1.1145,
+      "step": 245
+    },
+    {
+      "epoch": 0.9104788341429563,
+      "grad_norm": 0.5243192315101624,
+      "learning_rate": 1.7645075470097024e-05,
+      "loss": 1.1238,
+      "step": 246
+    },
+    {
+      "epoch": 0.9141799676150821,
+      "grad_norm": 0.4946383237838745,
+      "learning_rate": 1.7617301573941296e-05,
+      "loss": 1.1248,
+      "step": 247
+    },
+    {
+      "epoch": 0.917881101087208,
+      "grad_norm": 0.4805106520652771,
+      "learning_rate": 1.758938698705884e-05,
+      "loss": 1.1303,
+      "step": 248
+    },
+    {
+      "epoch": 0.9215822345593337,
+      "grad_norm": 0.44972893595695496,
+      "learning_rate": 1.7561332225029022e-05,
+      "loss": 1.1356,
+      "step": 249
+    },
+    {
+      "epoch": 0.9252833680314596,
+      "grad_norm": 0.45467665791511536,
+      "learning_rate": 1.7533137806020226e-05,
+      "loss": 1.0766,
+      "step": 250
+    },
+    {
+      "epoch": 0.9289845015035855,
+      "grad_norm": 0.5250957608222961,
+      "learning_rate": 1.7504804250780292e-05,
+      "loss": 1.1021,
+      "step": 251
+    },
+    {
+      "epoch": 0.9326856349757113,
+      "grad_norm": 0.3975278437137604,
+      "learning_rate": 1.747633208262688e-05,
+      "loss": 1.115,
+      "step": 252
+    },
+    {
+      "epoch": 0.9363867684478372,
+      "grad_norm": 0.529544472694397,
+      "learning_rate": 1.744772182743782e-05,
+      "loss": 1.1115,
+      "step": 253
+    },
+    {
+      "epoch": 0.9400879019199629,
+      "grad_norm": 0.460066556930542,
+      "learning_rate": 1.74189740136414e-05,
+      "loss": 1.1012,
+      "step": 254
+    },
+    {
+      "epoch": 0.9437890353920888,
+      "grad_norm": 0.4442214071750641,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 1.1247,
+      "step": 255
+    },
+    {
+      "epoch": 0.9474901688642147,
+      "grad_norm": 0.5348288416862488,
+      "learning_rate": 1.736106783663326e-05,
+      "loss": 1.0952,
+      "step": 256
+    },
+    {
+      "epoch": 0.9511913023363405,
+      "grad_norm": 0.3909313678741455,
+      "learning_rate": 1.7331910542942298e-05,
+      "loss": 1.1331,
+      "step": 257
+    },
+    {
+      "epoch": 0.9548924358084664,
+      "grad_norm": 0.49731630086898804,
+      "learning_rate": 1.7302617829665725e-05,
+      "loss": 1.1077,
+      "step": 258
+    },
+    {
+      "epoch": 0.9585935692805921,
+      "grad_norm": 0.4206913709640503,
+      "learning_rate": 1.7273190237836757e-05,
+      "loss": 1.1321,
+      "step": 259
+    },
+    {
+      "epoch": 0.962294702752718,
+      "grad_norm": 0.5688621401786804,
+      "learning_rate": 1.7243628310979793e-05,
+      "loss": 1.1318,
+      "step": 260
+    },
+    {
+      "epoch": 0.9659958362248439,
+      "grad_norm": 0.4344209134578705,
+      "learning_rate": 1.7213932595100384e-05,
+      "loss": 1.1188,
+      "step": 261
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.482854425907135,
+      "learning_rate": 1.7184103638675157e-05,
+      "loss": 1.116,
+      "step": 262
+    },
+    {
+      "epoch": 0.9733981031690956,
+      "grad_norm": 0.4521266520023346,
+      "learning_rate": 1.715414199264168e-05,
+      "loss": 1.0995,
+      "step": 263
+    },
+    {
+      "epoch": 0.9770992366412213,
+      "grad_norm": 0.47049805521965027,
+      "learning_rate": 1.7124048210388268e-05,
+      "loss": 1.1207,
+      "step": 264
+    },
+    {
+      "epoch": 0.9808003701133472,
+      "grad_norm": 0.3913280963897705,
+      "learning_rate": 1.709382284774379e-05,
+      "loss": 1.1493,
+      "step": 265
+    },
+    {
+      "epoch": 0.9845015035854731,
+      "grad_norm": 0.3968203067779541,
+      "learning_rate": 1.706346646296739e-05,
+      "loss": 1.1241,
+      "step": 266
+    },
+    {
+      "epoch": 0.9882026370575989,
+      "grad_norm": 0.46026578545570374,
+      "learning_rate": 1.7032979616738167e-05,
+      "loss": 1.1181,
+      "step": 267
+    },
+    {
+      "epoch": 0.9919037705297248,
+      "grad_norm": 0.3910259008407593,
+      "learning_rate": 1.7002362872144843e-05,
+      "loss": 1.1082,
+      "step": 268
+    },
+    {
+      "epoch": 0.9956049040018505,
+      "grad_norm": 0.40289193391799927,
+      "learning_rate": 1.697161679467534e-05,
+      "loss": 1.1013,
+      "step": 269
+    },
+    {
+      "epoch": 0.9993060374739764,
+      "grad_norm": 0.4233797788619995,
+      "learning_rate": 1.6940741952206342e-05,
+      "loss": 1.1123,
+      "step": 270
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4233797788619995,
+      "learning_rate": 1.6909738914992812e-05,
+      "loss": 1.1457,
+      "step": 271
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 813,
+  "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": 333261142228992.0,
+  "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:e43d868fe1564fb914d2dd355a72fcee2b77979729717f01381d32ca71a38ea3
+size 7672

zero_to_fp32.py

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