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 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "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 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

global_step300/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a48b8abdc62ca2162ec7309cb120f3caeb27d6198d00efaf134ef391b18eb292
+size 12067415329

global_step300/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db9f30f94a2922483cd23c7da113a7ec94fe37985672f704e42fca939dff1d6
+size 12067417953

global_step300/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407b47ccd39022e7a8d00c03a90ccf14528afe0c9db190f8afba5a7351afe426
+size 12067418081

global_step300/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9553960f0b9546e0b8aa82ebc4ec8083f8d34bc28de9c368b6143bb71b088a51
+size 12067418081

global_step300/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a737aa7bfb268e3c284de14d5be9e32f8ff92191dc2273b45da9ae6fc33f9f3b
+size 8045052005

latest

@@ -0,0 +1 @@
+global_step300

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1335c8fcb2fa33af13bf8e313eb96f8d13ce442cd91ce46106f9bf29f9ef9b
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfdedd7f16d4b41dcf5b0eed45a5a52b2c944272d203ebaa8162e9173e452525
+size 3855679144

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 8822848512
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "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 sha256:7f91f87bd9a92e8739289f46162ef308559319763234c64c5b77db9ec569f87f
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7d39b8b541e3fd455fdaac992f8e531a8b6ecbd342d84bd34ce103caf8c4829
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ff092a382271ec0416bca1eaebe1589a5c027148f661f515a99be89a41550e9
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee31a8654359133d1c40cfb2da8b7350b44cc7eec9bf923c997643420f7061d
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2823a2f9c962c12c9079ef3645dfbbd6f2b1de7f2f0148d54b447c098b659469
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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": "<|endoftext|>",
+  "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 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5744833639192531,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019149445463975106,
+      "grad_norm": 2.4355921745300293,
+      "learning_rate": 0.0,
+      "loss": 0.5195,
+      "step": 1
+    },
+    {
+      "epoch": 0.003829889092795021,
+      "grad_norm": 2.444409132003784,
+      "learning_rate": 6.369426751592358e-08,
+      "loss": 0.543,
+      "step": 2
+    },
+    {
+      "epoch": 0.005744833639192532,
+      "grad_norm": 2.3453526496887207,
+      "learning_rate": 1.2738853503184715e-07,
+      "loss": 0.5273,
+      "step": 3
+    },
+    {
+      "epoch": 0.007659778185590042,
+      "grad_norm": 2.0779857635498047,
+      "learning_rate": 1.9108280254777072e-07,
+      "loss": 0.4805,
+      "step": 4
+    },
+    {
+      "epoch": 0.009574722731987553,
+      "grad_norm": 2.307081699371338,
+      "learning_rate": 2.547770700636943e-07,
+      "loss": 0.4609,
+      "step": 5
+    },
+    {
+      "epoch": 0.011489667278385064,
+      "grad_norm": 2.1092047691345215,
+      "learning_rate": 3.1847133757961787e-07,
+      "loss": 0.4219,
+      "step": 6
+    },
+    {
+      "epoch": 0.013404611824782574,
+      "grad_norm": 2.4406685829162598,
+      "learning_rate": 3.8216560509554143e-07,
+      "loss": 0.5273,
+      "step": 7
+    },
+    {
+      "epoch": 0.015319556371180085,
+      "grad_norm": 2.5096800327301025,
+      "learning_rate": 4.45859872611465e-07,
+      "loss": 0.5781,
+      "step": 8
+    },
+    {
+      "epoch": 0.017234500917577594,
+      "grad_norm": 2.025543451309204,
+      "learning_rate": 5.095541401273886e-07,
+      "loss": 0.4355,
+      "step": 9
+    },
+    {
+      "epoch": 0.019149445463975106,
+      "grad_norm": 2.0597877502441406,
+      "learning_rate": 5.732484076433121e-07,
+      "loss": 0.4902,
+      "step": 10
+    },
+    {
+      "epoch": 0.021064390010372615,
+      "grad_norm": 2.492584466934204,
+      "learning_rate": 6.369426751592357e-07,
+      "loss": 0.6055,
+      "step": 11
+    },
+    {
+      "epoch": 0.022979334556770127,
+      "grad_norm": 1.8612791299819946,
+      "learning_rate": 7.006369426751592e-07,
+      "loss": 0.457,
+      "step": 12
+    },
+    {
+      "epoch": 0.024894279103167636,
+      "grad_norm": 1.9757673740386963,
+      "learning_rate": 7.643312101910829e-07,
+      "loss": 0.5586,
+      "step": 13
+    },
+    {
+      "epoch": 0.02680922364956515,
+      "grad_norm": 1.6426618099212646,
+      "learning_rate": 8.280254777070064e-07,
+      "loss": 0.4453,
+      "step": 14
+    },
+    {
+      "epoch": 0.028724168195962657,
+      "grad_norm": 1.8673598766326904,
+      "learning_rate": 8.9171974522293e-07,
+      "loss": 0.5586,
+      "step": 15
+    },
+    {
+      "epoch": 0.03063911274236017,
+      "grad_norm": 1.8291136026382446,
+      "learning_rate": 9.554140127388537e-07,
+      "loss": 0.5156,
+      "step": 16
+    },
+    {
+      "epoch": 0.03255405728875768,
+      "grad_norm": 1.7877495288848877,
+      "learning_rate": 1.0191082802547772e-06,
+      "loss": 0.5586,
+      "step": 17
+    },
+    {
+      "epoch": 0.03446900183515519,
+      "grad_norm": 1.5062263011932373,
+      "learning_rate": 1.0828025477707007e-06,
+      "loss": 0.5273,
+      "step": 18
+    },
+    {
+      "epoch": 0.0363839463815527,
+      "grad_norm": 1.7692209482192993,
+      "learning_rate": 1.1464968152866242e-06,
+      "loss": 0.6055,
+      "step": 19
+    },
+    {
+      "epoch": 0.03829889092795021,
+      "grad_norm": 1.4987772703170776,
+      "learning_rate": 1.210191082802548e-06,
+      "loss": 0.5156,
+      "step": 20
+    },
+    {
+      "epoch": 0.040213835474347724,
+      "grad_norm": 1.499037742614746,
+      "learning_rate": 1.2738853503184715e-06,
+      "loss": 0.5625,
+      "step": 21
+    },
+    {
+      "epoch": 0.04212878002074523,
+      "grad_norm": 1.3796921968460083,
+      "learning_rate": 1.337579617834395e-06,
+      "loss": 0.5312,
+      "step": 22
+    },
+    {
+      "epoch": 0.04404372456714274,
+      "grad_norm": 1.1836010217666626,
+      "learning_rate": 1.4012738853503185e-06,
+      "loss": 0.5,
+      "step": 23
+    },
+    {
+      "epoch": 0.045958669113540254,
+      "grad_norm": 0.9325675964355469,
+      "learning_rate": 1.4649681528662422e-06,
+      "loss": 0.5117,
+      "step": 24
+    },
+    {
+      "epoch": 0.047873613659937767,
+      "grad_norm": 0.9935901165008545,
+      "learning_rate": 1.5286624203821657e-06,
+      "loss": 0.4707,
+      "step": 25
+    },
+    {
+      "epoch": 0.04978855820633527,
+      "grad_norm": 1.0810490846633911,
+      "learning_rate": 1.5923566878980892e-06,
+      "loss": 0.4453,
+      "step": 26
+    },
+    {
+      "epoch": 0.051703502752732784,
+      "grad_norm": 1.1079798936843872,
+      "learning_rate": 1.6560509554140127e-06,
+      "loss": 0.4844,
+      "step": 27
+    },
+    {
+      "epoch": 0.0536184472991303,
+      "grad_norm": 1.0377357006072998,
+      "learning_rate": 1.7197452229299363e-06,
+      "loss": 0.498,
+      "step": 28
+    },
+    {
+      "epoch": 0.05553339184552781,
+      "grad_norm": 0.7516281604766846,
+      "learning_rate": 1.78343949044586e-06,
+      "loss": 0.3398,
+      "step": 29
+    },
+    {
+      "epoch": 0.057448336391925314,
+      "grad_norm": 0.7505989670753479,
+      "learning_rate": 1.8471337579617835e-06,
+      "loss": 0.457,
+      "step": 30
+    },
+    {
+      "epoch": 0.05936328093832283,
+      "grad_norm": 0.6712049245834351,
+      "learning_rate": 1.9108280254777074e-06,
+      "loss": 0.4922,
+      "step": 31
+    },
+    {
+      "epoch": 0.06127822548472034,
+      "grad_norm": 0.7440502047538757,
+      "learning_rate": 1.974522292993631e-06,
+      "loss": 0.4648,
+      "step": 32
+    },
+    {
+      "epoch": 0.06319317003111785,
+      "grad_norm": 0.7507379055023193,
+      "learning_rate": 2.0382165605095544e-06,
+      "loss": 0.4102,
+      "step": 33
+    },
+    {
+      "epoch": 0.06510811457751536,
+      "grad_norm": 1.0105549097061157,
+      "learning_rate": 2.101910828025478e-06,
+      "loss": 0.4844,
+      "step": 34
+    },
+    {
+      "epoch": 0.06702305912391288,
+      "grad_norm": 0.8056528568267822,
+      "learning_rate": 2.1656050955414015e-06,
+      "loss": 0.4023,
+      "step": 35
+    },
+    {
+      "epoch": 0.06893800367031037,
+      "grad_norm": 0.80513596534729,
+      "learning_rate": 2.229299363057325e-06,
+      "loss": 0.4531,
+      "step": 36
+    },
+    {
+      "epoch": 0.07085294821670789,
+      "grad_norm": 0.6895999908447266,
+      "learning_rate": 2.2929936305732485e-06,
+      "loss": 0.416,
+      "step": 37
+    },
+    {
+      "epoch": 0.0727678927631054,
+      "grad_norm": 0.6521788835525513,
+      "learning_rate": 2.356687898089172e-06,
+      "loss": 0.3281,
+      "step": 38
+    },
+    {
+      "epoch": 0.07468283730950291,
+      "grad_norm": 1.1881077289581299,
+      "learning_rate": 2.420382165605096e-06,
+      "loss": 0.4629,
+      "step": 39
+    },
+    {
+      "epoch": 0.07659778185590042,
+      "grad_norm": 0.7610136866569519,
+      "learning_rate": 2.4840764331210194e-06,
+      "loss": 0.4922,
+      "step": 40
+    },
+    {
+      "epoch": 0.07851272640229794,
+      "grad_norm": 0.6756831407546997,
+      "learning_rate": 2.547770700636943e-06,
+      "loss": 0.5117,
+      "step": 41
+    },
+    {
+      "epoch": 0.08042767094869545,
+      "grad_norm": 0.5855818390846252,
+      "learning_rate": 2.6114649681528665e-06,
+      "loss": 0.4277,
+      "step": 42
+    },
+    {
+      "epoch": 0.08234261549509296,
+      "grad_norm": 0.5638097524642944,
+      "learning_rate": 2.67515923566879e-06,
+      "loss": 0.4629,
+      "step": 43
+    },
+    {
+      "epoch": 0.08425756004149046,
+      "grad_norm": 0.4795784056186676,
+      "learning_rate": 2.7388535031847135e-06,
+      "loss": 0.457,
+      "step": 44
+    },
+    {
+      "epoch": 0.08617250458788797,
+      "grad_norm": 0.44129636883735657,
+      "learning_rate": 2.802547770700637e-06,
+      "loss": 0.4199,
+      "step": 45
+    },
+    {
+      "epoch": 0.08808744913428548,
+      "grad_norm": 0.5452600717544556,
+      "learning_rate": 2.8662420382165605e-06,
+      "loss": 0.4883,
+      "step": 46
+    },
+    {
+      "epoch": 0.090002393680683,
+      "grad_norm": 0.5549207925796509,
+      "learning_rate": 2.9299363057324844e-06,
+      "loss": 0.4336,
+      "step": 47
+    },
+    {
+      "epoch": 0.09191733822708051,
+      "grad_norm": 0.4318218231201172,
+      "learning_rate": 2.993630573248408e-06,
+      "loss": 0.3633,
+      "step": 48
+    },
+    {
+      "epoch": 0.09383228277347802,
+      "grad_norm": 0.4986816942691803,
+      "learning_rate": 3.0573248407643314e-06,
+      "loss": 0.3926,
+      "step": 49
+    },
+    {
+      "epoch": 0.09574722731987553,
+      "grad_norm": 0.4866129159927368,
+      "learning_rate": 3.121019108280255e-06,
+      "loss": 0.418,
+      "step": 50
+    },
+    {
+      "epoch": 0.09766217186627305,
+      "grad_norm": 0.6105746626853943,
+      "learning_rate": 3.1847133757961785e-06,
+      "loss": 0.4707,
+      "step": 51
+    },
+    {
+      "epoch": 0.09957711641267054,
+      "grad_norm": 0.5020173192024231,
+      "learning_rate": 3.248407643312102e-06,
+      "loss": 0.4707,
+      "step": 52
+    },
+    {
+      "epoch": 0.10149206095906806,
+      "grad_norm": 0.36393049359321594,
+      "learning_rate": 3.3121019108280255e-06,
+      "loss": 0.3926,
+      "step": 53
+    },
+    {
+      "epoch": 0.10340700550546557,
+      "grad_norm": 0.45811325311660767,
+      "learning_rate": 3.375796178343949e-06,
+      "loss": 0.4492,
+      "step": 54
+    },
+    {
+      "epoch": 0.10532195005186308,
+      "grad_norm": 0.5363308191299438,
+      "learning_rate": 3.4394904458598725e-06,
+      "loss": 0.3613,
+      "step": 55
+    },
+    {
+      "epoch": 0.1072368945982606,
+      "grad_norm": 0.48611095547676086,
+      "learning_rate": 3.5031847133757964e-06,
+      "loss": 0.4434,
+      "step": 56
+    },
+    {
+      "epoch": 0.1091518391446581,
+      "grad_norm": 0.4395770728588104,
+      "learning_rate": 3.56687898089172e-06,
+      "loss": 0.4668,
+      "step": 57
+    },
+    {
+      "epoch": 0.11106678369105562,
+      "grad_norm": 0.43419352173805237,
+      "learning_rate": 3.6305732484076435e-06,
+      "loss": 0.4512,
+      "step": 58
+    },
+    {
+      "epoch": 0.11298172823745313,
+      "grad_norm": 0.4470672607421875,
+      "learning_rate": 3.694267515923567e-06,
+      "loss": 0.4863,
+      "step": 59
+    },
+    {
+      "epoch": 0.11489667278385063,
+      "grad_norm": 0.40022385120391846,
+      "learning_rate": 3.757961783439491e-06,
+      "loss": 0.4141,
+      "step": 60
+    },
+    {
+      "epoch": 0.11681161733024814,
+      "grad_norm": 0.4839700162410736,
+      "learning_rate": 3.821656050955415e-06,
+      "loss": 0.543,
+      "step": 61
+    },
+    {
+      "epoch": 0.11872656187664565,
+      "grad_norm": 0.37022727727890015,
+      "learning_rate": 3.885350318471338e-06,
+      "loss": 0.4629,
+      "step": 62
+    },
+    {
+      "epoch": 0.12064150642304317,
+      "grad_norm": 0.4015008509159088,
+      "learning_rate": 3.949044585987262e-06,
+      "loss": 0.4473,
+      "step": 63
+    },
+    {
+      "epoch": 0.12255645096944068,
+      "grad_norm": 0.33814293146133423,
+      "learning_rate": 4.012738853503185e-06,
+      "loss": 0.3594,
+      "step": 64
+    },
+    {
+      "epoch": 0.12447139551583819,
+      "grad_norm": 0.38957205414772034,
+      "learning_rate": 4.076433121019109e-06,
+      "loss": 0.4688,
+      "step": 65
+    },
+    {
+      "epoch": 0.1263863400622357,
+      "grad_norm": 0.34749555587768555,
+      "learning_rate": 4.140127388535032e-06,
+      "loss": 0.4004,
+      "step": 66
+    },
+    {
+      "epoch": 0.12830128460863321,
+      "grad_norm": 0.408210813999176,
+      "learning_rate": 4.203821656050956e-06,
+      "loss": 0.4941,
+      "step": 67
+    },
+    {
+      "epoch": 0.13021622915503073,
+      "grad_norm": 0.35355207324028015,
+      "learning_rate": 4.26751592356688e-06,
+      "loss": 0.3594,
+      "step": 68
+    },
+    {
+      "epoch": 0.13213117370142824,
+      "grad_norm": 0.48519861698150635,
+      "learning_rate": 4.331210191082803e-06,
+      "loss": 0.4902,
+      "step": 69
+    },
+    {
+      "epoch": 0.13404611824782575,
+      "grad_norm": 0.3278568387031555,
+      "learning_rate": 4.394904458598727e-06,
+      "loss": 0.3945,
+      "step": 70
+    },
+    {
+      "epoch": 0.13596106279422326,
+      "grad_norm": 0.4168219566345215,
+      "learning_rate": 4.45859872611465e-06,
+      "loss": 0.416,
+      "step": 71
+    },
+    {
+      "epoch": 0.13787600734062075,
+      "grad_norm": 0.3659290373325348,
+      "learning_rate": 4.522292993630574e-06,
+      "loss": 0.4375,
+      "step": 72
+    },
+    {
+      "epoch": 0.13979095188701826,
+      "grad_norm": 0.3873862624168396,
+      "learning_rate": 4.585987261146497e-06,
+      "loss": 0.3965,
+      "step": 73
+    },
+    {
+      "epoch": 0.14170589643341577,
+      "grad_norm": 0.38224056363105774,
+      "learning_rate": 4.649681528662421e-06,
+      "loss": 0.4648,
+      "step": 74
+    },
+    {
+      "epoch": 0.14362084097981329,
+      "grad_norm": 0.36365070939064026,
+      "learning_rate": 4.713375796178344e-06,
+      "loss": 0.3672,
+      "step": 75
+    },
+    {
+      "epoch": 0.1455357855262108,
+      "grad_norm": 0.3808673918247223,
+      "learning_rate": 4.777070063694268e-06,
+      "loss": 0.3789,
+      "step": 76
+    },
+    {
+      "epoch": 0.1474507300726083,
+      "grad_norm": 0.3691989779472351,
+      "learning_rate": 4.840764331210192e-06,
+      "loss": 0.4258,
+      "step": 77
+    },
+    {
+      "epoch": 0.14936567461900582,
+      "grad_norm": 0.4533417820930481,
+      "learning_rate": 4.904458598726115e-06,
+      "loss": 0.5,
+      "step": 78
+    },
+    {
+      "epoch": 0.15128061916540333,
+      "grad_norm": 0.34389302134513855,
+      "learning_rate": 4.968152866242039e-06,
+      "loss": 0.3828,
+      "step": 79
+    },
+    {
+      "epoch": 0.15319556371180085,
+      "grad_norm": 0.35934531688690186,
+      "learning_rate": 5.031847133757962e-06,
+      "loss": 0.4375,
+      "step": 80
+    },
+    {
+      "epoch": 0.15511050825819836,
+      "grad_norm": 0.3186410367488861,
+      "learning_rate": 5.095541401273886e-06,
+      "loss": 0.3848,
+      "step": 81
+    },
+    {
+      "epoch": 0.15702545280459587,
+      "grad_norm": 0.3838176727294922,
+      "learning_rate": 5.159235668789809e-06,
+      "loss": 0.3379,
+      "step": 82
+    },
+    {
+      "epoch": 0.15894039735099338,
+      "grad_norm": 0.3711152672767639,
+      "learning_rate": 5.222929936305733e-06,
+      "loss": 0.3906,
+      "step": 83
+    },
+    {
+      "epoch": 0.1608553418973909,
+      "grad_norm": 0.33732864260673523,
+      "learning_rate": 5.286624203821657e-06,
+      "loss": 0.4316,
+      "step": 84
+    },
+    {
+      "epoch": 0.1627702864437884,
+      "grad_norm": 0.4067969024181366,
+      "learning_rate": 5.35031847133758e-06,
+      "loss": 0.3418,
+      "step": 85
+    },
+    {
+      "epoch": 0.16468523099018592,
+      "grad_norm": 0.3334014415740967,
+      "learning_rate": 5.414012738853504e-06,
+      "loss": 0.3398,
+      "step": 86
+    },
+    {
+      "epoch": 0.16660017553658343,
+      "grad_norm": 0.30455130338668823,
+      "learning_rate": 5.477707006369427e-06,
+      "loss": 0.3594,
+      "step": 87
+    },
+    {
+      "epoch": 0.16851512008298092,
+      "grad_norm": 0.445254385471344,
+      "learning_rate": 5.541401273885351e-06,
+      "loss": 0.457,
+      "step": 88
+    },
+    {
+      "epoch": 0.17043006462937843,
+      "grad_norm": 0.3656286299228668,
+      "learning_rate": 5.605095541401274e-06,
+      "loss": 0.4199,
+      "step": 89
+    },
+    {
+      "epoch": 0.17234500917577594,
+      "grad_norm": 0.40646082162857056,
+      "learning_rate": 5.668789808917198e-06,
+      "loss": 0.3984,
+      "step": 90
+    },
+    {
+      "epoch": 0.17425995372217346,
+      "grad_norm": 0.3945332467556,
+      "learning_rate": 5.732484076433121e-06,
+      "loss": 0.3594,
+      "step": 91
+    },
+    {
+      "epoch": 0.17617489826857097,
+      "grad_norm": 0.3301292359828949,
+      "learning_rate": 5.796178343949045e-06,
+      "loss": 0.4199,
+      "step": 92
+    },
+    {
+      "epoch": 0.17808984281496848,
+      "grad_norm": 0.3358660042285919,
+      "learning_rate": 5.859872611464969e-06,
+      "loss": 0.3535,
+      "step": 93
+    },
+    {
+      "epoch": 0.180004787361366,
+      "grad_norm": 0.35072633624076843,
+      "learning_rate": 5.923566878980892e-06,
+      "loss": 0.4414,
+      "step": 94
+    },
+    {
+      "epoch": 0.1819197319077635,
+      "grad_norm": 0.3340066075325012,
+      "learning_rate": 5.987261146496816e-06,
+      "loss": 0.3945,
+      "step": 95
+    },
+    {
+      "epoch": 0.18383467645416102,
+      "grad_norm": 0.31716787815093994,
+      "learning_rate": 6.050955414012739e-06,
+      "loss": 0.3516,
+      "step": 96
+    },
+    {
+      "epoch": 0.18574962100055853,
+      "grad_norm": 0.3251139223575592,
+      "learning_rate": 6.114649681528663e-06,
+      "loss": 0.3848,
+      "step": 97
+    },
+    {
+      "epoch": 0.18766456554695604,
+      "grad_norm": 0.30106034874916077,
+      "learning_rate": 6.178343949044586e-06,
+      "loss": 0.3555,
+      "step": 98
+    },
+    {
+      "epoch": 0.18957951009335355,
+      "grad_norm": 0.3289436399936676,
+      "learning_rate": 6.24203821656051e-06,
+      "loss": 0.3203,
+      "step": 99
+    },
+    {
+      "epoch": 0.19149445463975107,
+      "grad_norm": 0.4102315902709961,
+      "learning_rate": 6.305732484076433e-06,
+      "loss": 0.4316,
+      "step": 100
+    },
+    {
+      "epoch": 0.19340939918614858,
+      "grad_norm": 0.34562960267066956,
+      "learning_rate": 6.369426751592357e-06,
+      "loss": 0.3496,
+      "step": 101
+    },
+    {
+      "epoch": 0.1953243437325461,
+      "grad_norm": 0.35827019810676575,
+      "learning_rate": 6.433121019108281e-06,
+      "loss": 0.3984,
+      "step": 102
+    },
+    {
+      "epoch": 0.19723928827894358,
+      "grad_norm": 0.33068418502807617,
+      "learning_rate": 6.496815286624204e-06,
+      "loss": 0.3105,
+      "step": 103
+    },
+    {
+      "epoch": 0.1991542328253411,
+      "grad_norm": 0.34721487760543823,
+      "learning_rate": 6.560509554140128e-06,
+      "loss": 0.4023,
+      "step": 104
+    },
+    {
+      "epoch": 0.2010691773717386,
+      "grad_norm": 0.409750759601593,
+      "learning_rate": 6.624203821656051e-06,
+      "loss": 0.4258,
+      "step": 105
+    },
+    {
+      "epoch": 0.2029841219181361,
+      "grad_norm": 0.3398571312427521,
+      "learning_rate": 6.687898089171975e-06,
+      "loss": 0.373,
+      "step": 106
+    },
+    {
+      "epoch": 0.20489906646453362,
+      "grad_norm": 0.34012889862060547,
+      "learning_rate": 6.751592356687898e-06,
+      "loss": 0.3379,
+      "step": 107
+    },
+    {
+      "epoch": 0.20681401101093114,
+      "grad_norm": 0.33973219990730286,
+      "learning_rate": 6.815286624203822e-06,
+      "loss": 0.3672,
+      "step": 108
+    },
+    {
+      "epoch": 0.20872895555732865,
+      "grad_norm": 0.3657017648220062,
+      "learning_rate": 6.878980891719745e-06,
+      "loss": 0.3457,
+      "step": 109
+    },
+    {
+      "epoch": 0.21064390010372616,
+      "grad_norm": 0.4519689679145813,
+      "learning_rate": 6.942675159235669e-06,
+      "loss": 0.3828,
+      "step": 110
+    },
+    {
+      "epoch": 0.21255884465012367,
+      "grad_norm": 0.3746054768562317,
+      "learning_rate": 7.006369426751593e-06,
+      "loss": 0.377,
+      "step": 111
+    },
+    {
+      "epoch": 0.2144737891965212,
+      "grad_norm": 0.4097052812576294,
+      "learning_rate": 7.070063694267516e-06,
+      "loss": 0.4609,
+      "step": 112
+    },
+    {
+      "epoch": 0.2163887337429187,
+      "grad_norm": 0.3271676003932953,
+      "learning_rate": 7.13375796178344e-06,
+      "loss": 0.3438,
+      "step": 113
+    },
+    {
+      "epoch": 0.2183036782893162,
+      "grad_norm": 0.3513050973415375,
+      "learning_rate": 7.197452229299363e-06,
+      "loss": 0.4375,
+      "step": 114
+    },
+    {
+      "epoch": 0.22021862283571372,
+      "grad_norm": 0.3622526228427887,
+      "learning_rate": 7.261146496815287e-06,
+      "loss": 0.4121,
+      "step": 115
+    },
+    {
+      "epoch": 0.22213356738211124,
+      "grad_norm": 0.3314346671104431,
+      "learning_rate": 7.32484076433121e-06,
+      "loss": 0.4023,
+      "step": 116
+    },
+    {
+      "epoch": 0.22404851192850875,
+      "grad_norm": 0.33853384852409363,
+      "learning_rate": 7.388535031847134e-06,
+      "loss": 0.3496,
+      "step": 117
+    },
+    {
+      "epoch": 0.22596345647490626,
+      "grad_norm": 0.3633553683757782,
+      "learning_rate": 7.452229299363057e-06,
+      "loss": 0.3613,
+      "step": 118
+    },
+    {
+      "epoch": 0.22787840102130374,
+      "grad_norm": 0.33034729957580566,
+      "learning_rate": 7.515923566878982e-06,
+      "loss": 0.3672,
+      "step": 119
+    },
+    {
+      "epoch": 0.22979334556770126,
+      "grad_norm": 0.6564728617668152,
+      "learning_rate": 7.579617834394906e-06,
+      "loss": 0.3672,
+      "step": 120
+    },
+    {
+      "epoch": 0.23170829011409877,
+      "grad_norm": 0.3335916996002197,
+      "learning_rate": 7.64331210191083e-06,
+      "loss": 0.3809,
+      "step": 121
+    },
+    {
+      "epoch": 0.23362323466049628,
+      "grad_norm": 0.3193455934524536,
+      "learning_rate": 7.707006369426753e-06,
+      "loss": 0.3086,
+      "step": 122
+    },
+    {
+      "epoch": 0.2355381792068938,
+      "grad_norm": 0.39426565170288086,
+      "learning_rate": 7.770700636942676e-06,
+      "loss": 0.3066,
+      "step": 123
+    },
+    {
+      "epoch": 0.2374531237532913,
+      "grad_norm": 0.3445550799369812,
+      "learning_rate": 7.8343949044586e-06,
+      "loss": 0.3652,
+      "step": 124
+    },
+    {
+      "epoch": 0.23936806829968882,
+      "grad_norm": 0.3657853901386261,
+      "learning_rate": 7.898089171974524e-06,
+      "loss": 0.3633,
+      "step": 125
+    },
+    {
+      "epoch": 0.24128301284608633,
+      "grad_norm": 0.36185649037361145,
+      "learning_rate": 7.961783439490447e-06,
+      "loss": 0.3438,
+      "step": 126
+    },
+    {
+      "epoch": 0.24319795739248384,
+      "grad_norm": 0.40025272965431213,
+      "learning_rate": 8.02547770700637e-06,
+      "loss": 0.3574,
+      "step": 127
+    },
+    {
+      "epoch": 0.24511290193888136,
+      "grad_norm": 0.4066087007522583,
+      "learning_rate": 8.089171974522295e-06,
+      "loss": 0.4668,
+      "step": 128
+    },
+    {
+      "epoch": 0.24702784648527887,
+      "grad_norm": 0.33924514055252075,
+      "learning_rate": 8.152866242038218e-06,
+      "loss": 0.3652,
+      "step": 129
+    },
+    {
+      "epoch": 0.24894279103167638,
+      "grad_norm": 0.347211629152298,
+      "learning_rate": 8.21656050955414e-06,
+      "loss": 0.3809,
+      "step": 130
+    },
+    {
+      "epoch": 0.2508577355780739,
+      "grad_norm": 0.35744917392730713,
+      "learning_rate": 8.280254777070064e-06,
+      "loss": 0.3828,
+      "step": 131
+    },
+    {
+      "epoch": 0.2527726801244714,
+      "grad_norm": 0.3828674256801605,
+      "learning_rate": 8.343949044585989e-06,
+      "loss": 0.416,
+      "step": 132
+    },
+    {
+      "epoch": 0.2546876246708689,
+      "grad_norm": 0.39746707677841187,
+      "learning_rate": 8.407643312101912e-06,
+      "loss": 0.4023,
+      "step": 133
+    },
+    {
+      "epoch": 0.25660256921726643,
+      "grad_norm": 0.35075193643569946,
+      "learning_rate": 8.471337579617835e-06,
+      "loss": 0.3828,
+      "step": 134
+    },
+    {
+      "epoch": 0.25851751376366394,
+      "grad_norm": 0.36559295654296875,
+      "learning_rate": 8.53503184713376e-06,
+      "loss": 0.3633,
+      "step": 135
+    },
+    {
+      "epoch": 0.26043245831006145,
+      "grad_norm": 0.3440432846546173,
+      "learning_rate": 8.598726114649683e-06,
+      "loss": 0.3418,
+      "step": 136
+    },
+    {
+      "epoch": 0.26234740285645897,
+      "grad_norm": 0.3704967796802521,
+      "learning_rate": 8.662420382165606e-06,
+      "loss": 0.3789,
+      "step": 137
+    },
+    {
+      "epoch": 0.2642623474028565,
+      "grad_norm": 0.3533952534198761,
+      "learning_rate": 8.726114649681529e-06,
+      "loss": 0.375,
+      "step": 138
+    },
+    {
+      "epoch": 0.266177291949254,
+      "grad_norm": 0.35461661219596863,
+      "learning_rate": 8.789808917197454e-06,
+      "loss": 0.3516,
+      "step": 139
+    },
+    {
+      "epoch": 0.2680922364956515,
+      "grad_norm": 0.36203712224960327,
+      "learning_rate": 8.853503184713377e-06,
+      "loss": 0.375,
+      "step": 140
+    },
+    {
+      "epoch": 0.270007181042049,
+      "grad_norm": 0.3293781876564026,
+      "learning_rate": 8.9171974522293e-06,
+      "loss": 0.3379,
+      "step": 141
+    },
+    {
+      "epoch": 0.27192212558844653,
+      "grad_norm": 0.32773709297180176,
+      "learning_rate": 8.980891719745225e-06,
+      "loss": 0.3379,
+      "step": 142
+    },
+    {
+      "epoch": 0.273837070134844,
+      "grad_norm": 0.4453182816505432,
+      "learning_rate": 9.044585987261148e-06,
+      "loss": 0.5117,
+      "step": 143
+    },
+    {
+      "epoch": 0.2757520146812415,
+      "grad_norm": 0.41457095742225647,
+      "learning_rate": 9.10828025477707e-06,
+      "loss": 0.3574,
+      "step": 144
+    },
+    {
+      "epoch": 0.277666959227639,
+      "grad_norm": 0.41834110021591187,
+      "learning_rate": 9.171974522292994e-06,
+      "loss": 0.3906,
+      "step": 145
+    },
+    {
+      "epoch": 0.2795819037740365,
+      "grad_norm": 0.35413509607315063,
+      "learning_rate": 9.235668789808919e-06,
+      "loss": 0.4336,
+      "step": 146
+    },
+    {
+      "epoch": 0.28149684832043403,
+      "grad_norm": 0.3722779154777527,
+      "learning_rate": 9.299363057324842e-06,
+      "loss": 0.3086,
+      "step": 147
+    },
+    {
+      "epoch": 0.28341179286683155,
+      "grad_norm": 0.3540852665901184,
+      "learning_rate": 9.363057324840765e-06,
+      "loss": 0.3633,
+      "step": 148
+    },
+    {
+      "epoch": 0.28532673741322906,
+      "grad_norm": 0.3304201662540436,
+      "learning_rate": 9.426751592356688e-06,
+      "loss": 0.3027,
+      "step": 149
+    },
+    {
+      "epoch": 0.28724168195962657,
+      "grad_norm": 0.3253211975097656,
+      "learning_rate": 9.490445859872613e-06,
+      "loss": 0.2773,
+      "step": 150
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 0.39088380336761475,
+      "learning_rate": 9.554140127388536e-06,
+      "loss": 0.3086,
+      "step": 151
+    },
+    {
+      "epoch": 0.2910715710524216,
+      "grad_norm": 0.3674003779888153,
+      "learning_rate": 9.617834394904459e-06,
+      "loss": 0.3867,
+      "step": 152
+    },
+    {
+      "epoch": 0.2929865155988191,
+      "grad_norm": 0.42949748039245605,
+      "learning_rate": 9.681528662420384e-06,
+      "loss": 0.3535,
+      "step": 153
+    },
+    {
+      "epoch": 0.2949014601452166,
+      "grad_norm": 0.3864225447177887,
+      "learning_rate": 9.745222929936307e-06,
+      "loss": 0.373,
+      "step": 154
+    },
+    {
+      "epoch": 0.29681640469161413,
+      "grad_norm": 0.4238653779029846,
+      "learning_rate": 9.80891719745223e-06,
+      "loss": 0.3789,
+      "step": 155
+    },
+    {
+      "epoch": 0.29873134923801165,
+      "grad_norm": 0.38426122069358826,
+      "learning_rate": 9.872611464968153e-06,
+      "loss": 0.332,
+      "step": 156
+    },
+    {
+      "epoch": 0.30064629378440916,
+      "grad_norm": 0.37728747725486755,
+      "learning_rate": 9.936305732484078e-06,
+      "loss": 0.375,
+      "step": 157
+    },
+    {
+      "epoch": 0.30256123833080667,
+      "grad_norm": 0.39007872343063354,
+      "learning_rate": 1e-05,
+      "loss": 0.4551,
+      "step": 158
+    },
+    {
+      "epoch": 0.3044761828772042,
+      "grad_norm": 0.41649481654167175,
+      "learning_rate": 9.999987624288363e-06,
+      "loss": 0.4238,
+      "step": 159
+    },
+    {
+      "epoch": 0.3063911274236017,
+      "grad_norm": 0.37433379888534546,
+      "learning_rate": 9.999950497214712e-06,
+      "loss": 0.3438,
+      "step": 160
+    },
+    {
+      "epoch": 0.3083060719699992,
+      "grad_norm": 0.42663007974624634,
+      "learning_rate": 9.999888618962839e-06,
+      "loss": 0.3105,
+      "step": 161
+    },
+    {
+      "epoch": 0.3102210165163967,
+      "grad_norm": 0.3587310314178467,
+      "learning_rate": 9.999801989839055e-06,
+      "loss": 0.3105,
+      "step": 162
+    },
+    {
+      "epoch": 0.31213596106279423,
+      "grad_norm": 0.35394129157066345,
+      "learning_rate": 9.999690610272203e-06,
+      "loss": 0.2832,
+      "step": 163
+    },
+    {
+      "epoch": 0.31405090560919174,
+      "grad_norm": 0.3573514223098755,
+      "learning_rate": 9.999554480813642e-06,
+      "loss": 0.3145,
+      "step": 164
+    },
+    {
+      "epoch": 0.31596585015558926,
+      "grad_norm": 0.38047319650650024,
+      "learning_rate": 9.999393602137252e-06,
+      "loss": 0.3008,
+      "step": 165
+    },
+    {
+      "epoch": 0.31788079470198677,
+      "grad_norm": 0.41491907835006714,
+      "learning_rate": 9.999207975039429e-06,
+      "loss": 0.3848,
+      "step": 166
+    },
+    {
+      "epoch": 0.3197957392483843,
+      "grad_norm": 0.3877142369747162,
+      "learning_rate": 9.998997600439078e-06,
+      "loss": 0.3594,
+      "step": 167
+    },
+    {
+      "epoch": 0.3217106837947818,
+      "grad_norm": 0.3370790481567383,
+      "learning_rate": 9.998762479377613e-06,
+      "loss": 0.2695,
+      "step": 168
+    },
+    {
+      "epoch": 0.3236256283411793,
+      "grad_norm": 0.4250260293483734,
+      "learning_rate": 9.998502613018952e-06,
+      "loss": 0.3008,
+      "step": 169
+    },
+    {
+      "epoch": 0.3255405728875768,
+      "grad_norm": 0.3558523952960968,
+      "learning_rate": 9.998218002649507e-06,
+      "loss": 0.2754,
+      "step": 170
+    },
+    {
+      "epoch": 0.32745551743397433,
+      "grad_norm": 0.3442358672618866,
+      "learning_rate": 9.99790864967818e-06,
+      "loss": 0.3008,
+      "step": 171
+    },
+    {
+      "epoch": 0.32937046198037184,
+      "grad_norm": 0.4215598702430725,
+      "learning_rate": 9.997574555636355e-06,
+      "loss": 0.3867,
+      "step": 172
+    },
+    {
+      "epoch": 0.33128540652676935,
+      "grad_norm": 0.422977089881897,
+      "learning_rate": 9.997215722177895e-06,
+      "loss": 0.3066,
+      "step": 173
+    },
+    {
+      "epoch": 0.33320035107316687,
+      "grad_norm": 0.3850831389427185,
+      "learning_rate": 9.996832151079127e-06,
+      "loss": 0.332,
+      "step": 174
+    },
+    {
+      "epoch": 0.3351152956195643,
+      "grad_norm": 0.46243324875831604,
+      "learning_rate": 9.996423844238836e-06,
+      "loss": 0.3613,
+      "step": 175
+    },
+    {
+      "epoch": 0.33703024016596184,
+      "grad_norm": 0.44479626417160034,
+      "learning_rate": 9.995990803678259e-06,
+      "loss": 0.3574,
+      "step": 176
+    },
+    {
+      "epoch": 0.33894518471235935,
+      "grad_norm": 0.4255305230617523,
+      "learning_rate": 9.995533031541069e-06,
+      "loss": 0.3711,
+      "step": 177
+    },
+    {
+      "epoch": 0.34086012925875686,
+      "grad_norm": 0.3565676510334015,
+      "learning_rate": 9.995050530093366e-06,
+      "loss": 0.3652,
+      "step": 178
+    },
+    {
+      "epoch": 0.3427750738051544,
+      "grad_norm": 0.5011817216873169,
+      "learning_rate": 9.994543301723674e-06,
+      "loss": 0.375,
+      "step": 179
+    },
+    {
+      "epoch": 0.3446900183515519,
+      "grad_norm": 0.4056403934955597,
+      "learning_rate": 9.994011348942915e-06,
+      "loss": 0.3418,
+      "step": 180
+    },
+    {
+      "epoch": 0.3466049628979494,
+      "grad_norm": 0.39417311549186707,
+      "learning_rate": 9.993454674384408e-06,
+      "loss": 0.3027,
+      "step": 181
+    },
+    {
+      "epoch": 0.3485199074443469,
+      "grad_norm": 0.31448638439178467,
+      "learning_rate": 9.992873280803848e-06,
+      "loss": 0.3066,
+      "step": 182
+    },
+    {
+      "epoch": 0.3504348519907444,
+      "grad_norm": 0.39453354477882385,
+      "learning_rate": 9.992267171079302e-06,
+      "loss": 0.3887,
+      "step": 183
+    },
+    {
+      "epoch": 0.35234979653714193,
+      "grad_norm": 0.36697134375572205,
+      "learning_rate": 9.991636348211185e-06,
+      "loss": 0.3301,
+      "step": 184
+    },
+    {
+      "epoch": 0.35426474108353945,
+      "grad_norm": 0.4324952960014343,
+      "learning_rate": 9.990980815322246e-06,
+      "loss": 0.375,
+      "step": 185
+    },
+    {
+      "epoch": 0.35617968562993696,
+      "grad_norm": 0.39873865246772766,
+      "learning_rate": 9.990300575657565e-06,
+      "loss": 0.3867,
+      "step": 186
+    },
+    {
+      "epoch": 0.35809463017633447,
+      "grad_norm": 0.40679872035980225,
+      "learning_rate": 9.989595632584518e-06,
+      "loss": 0.3711,
+      "step": 187
+    },
+    {
+      "epoch": 0.360009574722732,
+      "grad_norm": 0.3605036437511444,
+      "learning_rate": 9.988865989592778e-06,
+      "loss": 0.3438,
+      "step": 188
+    },
+    {
+      "epoch": 0.3619245192691295,
+      "grad_norm": 0.4955857992172241,
+      "learning_rate": 9.988111650294279e-06,
+      "loss": 0.2969,
+      "step": 189
+    },
+    {
+      "epoch": 0.363839463815527,
+      "grad_norm": 0.3720203936100006,
+      "learning_rate": 9.987332618423221e-06,
+      "loss": 0.3633,
+      "step": 190
+    },
+    {
+      "epoch": 0.3657544083619245,
+      "grad_norm": 0.4176885187625885,
+      "learning_rate": 9.986528897836032e-06,
+      "loss": 0.3672,
+      "step": 191
+    },
+    {
+      "epoch": 0.36766935290832203,
+      "grad_norm": 0.38222536444664,
+      "learning_rate": 9.985700492511356e-06,
+      "loss": 0.4141,
+      "step": 192
+    },
+    {
+      "epoch": 0.36958429745471955,
+      "grad_norm": 0.35066160559654236,
+      "learning_rate": 9.984847406550036e-06,
+      "loss": 0.3438,
+      "step": 193
+    },
+    {
+      "epoch": 0.37149924200111706,
+      "grad_norm": 0.35708916187286377,
+      "learning_rate": 9.983969644175092e-06,
+      "loss": 0.291,
+      "step": 194
+    },
+    {
+      "epoch": 0.37341418654751457,
+      "grad_norm": 0.36304759979248047,
+      "learning_rate": 9.983067209731696e-06,
+      "loss": 0.3672,
+      "step": 195
+    },
+    {
+      "epoch": 0.3753291310939121,
+      "grad_norm": 0.3975924849510193,
+      "learning_rate": 9.982140107687156e-06,
+      "loss": 0.3262,
+      "step": 196
+    },
+    {
+      "epoch": 0.3772440756403096,
+      "grad_norm": 0.40323784947395325,
+      "learning_rate": 9.98118834263089e-06,
+      "loss": 0.3633,
+      "step": 197
+    },
+    {
+      "epoch": 0.3791590201867071,
+      "grad_norm": 0.4162772595882416,
+      "learning_rate": 9.980211919274407e-06,
+      "loss": 0.4023,
+      "step": 198
+    },
+    {
+      "epoch": 0.3810739647331046,
+      "grad_norm": 0.3952171206474304,
+      "learning_rate": 9.979210842451282e-06,
+      "loss": 0.3438,
+      "step": 199
+    },
+    {
+      "epoch": 0.38298890927950213,
+      "grad_norm": 0.3455185890197754,
+      "learning_rate": 9.978185117117126e-06,
+      "loss": 0.3164,
+      "step": 200
+    },
+    {
+      "epoch": 0.38490385382589964,
+      "grad_norm": 0.3772539794445038,
+      "learning_rate": 9.977134748349575e-06,
+      "loss": 0.3516,
+      "step": 201
+    },
+    {
+      "epoch": 0.38681879837229716,
+      "grad_norm": 0.284085750579834,
+      "learning_rate": 9.976059741348252e-06,
+      "loss": 0.21,
+      "step": 202
+    },
+    {
+      "epoch": 0.38873374291869467,
+      "grad_norm": 0.4230060875415802,
+      "learning_rate": 9.974960101434747e-06,
+      "loss": 0.3301,
+      "step": 203
+    },
+    {
+      "epoch": 0.3906486874650922,
+      "grad_norm": 0.384288489818573,
+      "learning_rate": 9.973835834052593e-06,
+      "loss": 0.3203,
+      "step": 204
+    },
+    {
+      "epoch": 0.3925636320114897,
+      "grad_norm": 0.3772657513618469,
+      "learning_rate": 9.972686944767231e-06,
+      "loss": 0.3672,
+      "step": 205
+    },
+    {
+      "epoch": 0.39447857655788715,
+      "grad_norm": 0.36377066373825073,
+      "learning_rate": 9.971513439265992e-06,
+      "loss": 0.3496,
+      "step": 206
+    },
+    {
+      "epoch": 0.39639352110428466,
+      "grad_norm": 0.5106296539306641,
+      "learning_rate": 9.970315323358061e-06,
+      "loss": 0.3164,
+      "step": 207
+    },
+    {
+      "epoch": 0.3983084656506822,
+      "grad_norm": 0.406767874956131,
+      "learning_rate": 9.969092602974453e-06,
+      "loss": 0.4023,
+      "step": 208
+    },
+    {
+      "epoch": 0.4002234101970797,
+      "grad_norm": 0.35188838839530945,
+      "learning_rate": 9.967845284167981e-06,
+      "loss": 0.3477,
+      "step": 209
+    },
+    {
+      "epoch": 0.4021383547434772,
+      "grad_norm": 0.37596458196640015,
+      "learning_rate": 9.96657337311323e-06,
+      "loss": 0.3398,
+      "step": 210
+    },
+    {
+      "epoch": 0.4040532992898747,
+      "grad_norm": 0.32428470253944397,
+      "learning_rate": 9.965276876106523e-06,
+      "loss": 0.2715,
+      "step": 211
+    },
+    {
+      "epoch": 0.4059682438362722,
+      "grad_norm": 0.4191044569015503,
+      "learning_rate": 9.963955799565885e-06,
+      "loss": 0.4102,
+      "step": 212
+    },
+    {
+      "epoch": 0.40788318838266974,
+      "grad_norm": 0.3697478175163269,
+      "learning_rate": 9.962610150031025e-06,
+      "loss": 0.3984,
+      "step": 213
+    },
+    {
+      "epoch": 0.40979813292906725,
+      "grad_norm": 0.4006584882736206,
+      "learning_rate": 9.96123993416329e-06,
+      "loss": 0.3691,
+      "step": 214
+    },
+    {
+      "epoch": 0.41171307747546476,
+      "grad_norm": 0.3929983079433441,
+      "learning_rate": 9.959845158745635e-06,
+      "loss": 0.3262,
+      "step": 215
+    },
+    {
+      "epoch": 0.4136280220218623,
+      "grad_norm": 0.4248427152633667,
+      "learning_rate": 9.9584258306826e-06,
+      "loss": 0.3477,
+      "step": 216
+    },
+    {
+      "epoch": 0.4155429665682598,
+      "grad_norm": 0.369737833738327,
+      "learning_rate": 9.956981957000261e-06,
+      "loss": 0.3945,
+      "step": 217
+    },
+    {
+      "epoch": 0.4174579111146573,
+      "grad_norm": 0.34655651450157166,
+      "learning_rate": 9.955513544846205e-06,
+      "loss": 0.2969,
+      "step": 218
+    },
+    {
+      "epoch": 0.4193728556610548,
+      "grad_norm": 0.4321710467338562,
+      "learning_rate": 9.954020601489488e-06,
+      "loss": 0.3398,
+      "step": 219
+    },
+    {
+      "epoch": 0.4212878002074523,
+      "grad_norm": 0.387251615524292,
+      "learning_rate": 9.952503134320606e-06,
+      "loss": 0.3223,
+      "step": 220
+    },
+    {
+      "epoch": 0.42320274475384984,
+      "grad_norm": 0.4663626551628113,
+      "learning_rate": 9.950961150851454e-06,
+      "loss": 0.4922,
+      "step": 221
+    },
+    {
+      "epoch": 0.42511768930024735,
+      "grad_norm": 0.3990941047668457,
+      "learning_rate": 9.949394658715289e-06,
+      "loss": 0.3965,
+      "step": 222
+    },
+    {
+      "epoch": 0.42703263384664486,
+      "grad_norm": 0.3907487988471985,
+      "learning_rate": 9.94780366566669e-06,
+      "loss": 0.3105,
+      "step": 223
+    },
+    {
+      "epoch": 0.4289475783930424,
+      "grad_norm": 0.3887116611003876,
+      "learning_rate": 9.946188179581529e-06,
+      "loss": 0.3008,
+      "step": 224
+    },
+    {
+      "epoch": 0.4308625229394399,
+      "grad_norm": 0.44479915499687195,
+      "learning_rate": 9.94454820845692e-06,
+      "loss": 0.4258,
+      "step": 225
+    },
+    {
+      "epoch": 0.4327774674858374,
+      "grad_norm": 0.3838413655757904,
+      "learning_rate": 9.942883760411188e-06,
+      "loss": 0.3496,
+      "step": 226
+    },
+    {
+      "epoch": 0.4346924120322349,
+      "grad_norm": 0.4151753783226013,
+      "learning_rate": 9.941194843683826e-06,
+      "loss": 0.4102,
+      "step": 227
+    },
+    {
+      "epoch": 0.4366073565786324,
+      "grad_norm": 0.32539334893226624,
+      "learning_rate": 9.939481466635448e-06,
+      "loss": 0.2852,
+      "step": 228
+    },
+    {
+      "epoch": 0.43852230112502993,
+      "grad_norm": 0.39479121565818787,
+      "learning_rate": 9.937743637747763e-06,
+      "loss": 0.3379,
+      "step": 229
+    },
+    {
+      "epoch": 0.44043724567142745,
+      "grad_norm": 0.39315953850746155,
+      "learning_rate": 9.935981365623516e-06,
+      "loss": 0.3477,
+      "step": 230
+    },
+    {
+      "epoch": 0.44235219021782496,
+      "grad_norm": 0.3778970539569855,
+      "learning_rate": 9.934194658986457e-06,
+      "loss": 0.3711,
+      "step": 231
+    },
+    {
+      "epoch": 0.44426713476422247,
+      "grad_norm": 0.3942454159259796,
+      "learning_rate": 9.93238352668129e-06,
+      "loss": 0.3789,
+      "step": 232
+    },
+    {
+      "epoch": 0.44618207931062,
+      "grad_norm": 0.3276035189628601,
+      "learning_rate": 9.930547977673638e-06,
+      "loss": 0.3242,
+      "step": 233
+    },
+    {
+      "epoch": 0.4480970238570175,
+      "grad_norm": 0.32192081212997437,
+      "learning_rate": 9.928688021049991e-06,
+      "loss": 0.2773,
+      "step": 234
+    },
+    {
+      "epoch": 0.450011968403415,
+      "grad_norm": 0.35930487513542175,
+      "learning_rate": 9.926803666017664e-06,
+      "loss": 0.3438,
+      "step": 235
+    },
+    {
+      "epoch": 0.4519269129498125,
+      "grad_norm": 0.3854064643383026,
+      "learning_rate": 9.924894921904748e-06,
+      "loss": 0.3652,
+      "step": 236
+    },
+    {
+      "epoch": 0.45384185749621003,
+      "grad_norm": 0.40004488825798035,
+      "learning_rate": 9.92296179816007e-06,
+      "loss": 0.3711,
+      "step": 237
+    },
+    {
+      "epoch": 0.4557568020426075,
+      "grad_norm": 0.37695586681365967,
+      "learning_rate": 9.921004304353147e-06,
+      "loss": 0.3477,
+      "step": 238
+    },
+    {
+      "epoch": 0.457671746589005,
+      "grad_norm": 0.3978940546512604,
+      "learning_rate": 9.919022450174126e-06,
+      "loss": 0.3672,
+      "step": 239
+    },
+    {
+      "epoch": 0.4595866911354025,
+      "grad_norm": 0.40706950426101685,
+      "learning_rate": 9.917016245433755e-06,
+      "loss": 0.2852,
+      "step": 240
+    },
+    {
+      "epoch": 0.4615016356818,
+      "grad_norm": 0.370563805103302,
+      "learning_rate": 9.914985700063312e-06,
+      "loss": 0.3535,
+      "step": 241
+    },
+    {
+      "epoch": 0.46341658022819754,
+      "grad_norm": 0.39702001214027405,
+      "learning_rate": 9.912930824114577e-06,
+      "loss": 0.3125,
+      "step": 242
+    },
+    {
+      "epoch": 0.46533152477459505,
+      "grad_norm": 0.35320210456848145,
+      "learning_rate": 9.910851627759773e-06,
+      "loss": 0.3281,
+      "step": 243
+    },
+    {
+      "epoch": 0.46724646932099256,
+      "grad_norm": 0.4427463710308075,
+      "learning_rate": 9.90874812129151e-06,
+      "loss": 0.3398,
+      "step": 244
+    },
+    {
+      "epoch": 0.4691614138673901,
+      "grad_norm": 0.35988548398017883,
+      "learning_rate": 9.906620315122745e-06,
+      "loss": 0.293,
+      "step": 245
+    },
+    {
+      "epoch": 0.4710763584137876,
+      "grad_norm": 0.39641326665878296,
+      "learning_rate": 9.904468219786727e-06,
+      "loss": 0.3184,
+      "step": 246
+    },
+    {
+      "epoch": 0.4729913029601851,
+      "grad_norm": 0.3900603652000427,
+      "learning_rate": 9.902291845936938e-06,
+      "loss": 0.3574,
+      "step": 247
+    },
+    {
+      "epoch": 0.4749062475065826,
+      "grad_norm": 0.45603853464126587,
+      "learning_rate": 9.900091204347048e-06,
+      "loss": 0.457,
+      "step": 248
+    },
+    {
+      "epoch": 0.4768211920529801,
+      "grad_norm": 0.3850320279598236,
+      "learning_rate": 9.897866305910861e-06,
+      "loss": 0.3457,
+      "step": 249
+    },
+    {
+      "epoch": 0.47873613659937764,
+      "grad_norm": 0.3480890095233917,
+      "learning_rate": 9.895617161642257e-06,
+      "loss": 0.2969,
+      "step": 250
+    },
+    {
+      "epoch": 0.48065108114577515,
+      "grad_norm": 0.4086163341999054,
+      "learning_rate": 9.893343782675138e-06,
+      "loss": 0.3594,
+      "step": 251
+    },
+    {
+      "epoch": 0.48256602569217266,
+      "grad_norm": 0.3559402823448181,
+      "learning_rate": 9.891046180263382e-06,
+      "loss": 0.2734,
+      "step": 252
+    },
+    {
+      "epoch": 0.4844809702385702,
+      "grad_norm": 0.3534909784793854,
+      "learning_rate": 9.888724365780768e-06,
+      "loss": 0.3301,
+      "step": 253
+    },
+    {
+      "epoch": 0.4863959147849677,
+      "grad_norm": 0.3884546756744385,
+      "learning_rate": 9.886378350720945e-06,
+      "loss": 0.3965,
+      "step": 254
+    },
+    {
+      "epoch": 0.4883108593313652,
+      "grad_norm": 0.364305704832077,
+      "learning_rate": 9.884008146697352e-06,
+      "loss": 0.2617,
+      "step": 255
+    },
+    {
+      "epoch": 0.4902258038777627,
+      "grad_norm": 0.33573174476623535,
+      "learning_rate": 9.881613765443174e-06,
+      "loss": 0.3184,
+      "step": 256
+    },
+    {
+      "epoch": 0.4921407484241602,
+      "grad_norm": 0.3591967821121216,
+      "learning_rate": 9.879195218811282e-06,
+      "loss": 0.2734,
+      "step": 257
+    },
+    {
+      "epoch": 0.49405569297055774,
+      "grad_norm": 0.39021801948547363,
+      "learning_rate": 9.876752518774167e-06,
+      "loss": 0.334,
+      "step": 258
+    },
+    {
+      "epoch": 0.49597063751695525,
+      "grad_norm": 0.36973780393600464,
+      "learning_rate": 9.87428567742389e-06,
+      "loss": 0.2812,
+      "step": 259
+    },
+    {
+      "epoch": 0.49788558206335276,
+      "grad_norm": 0.3602698743343353,
+      "learning_rate": 9.87179470697202e-06,
+      "loss": 0.2793,
+      "step": 260
+    },
+    {
+      "epoch": 0.4998005266097503,
+      "grad_norm": 0.4194125831127167,
+      "learning_rate": 9.86927961974957e-06,
+      "loss": 0.3711,
+      "step": 261
+    },
+    {
+      "epoch": 0.5017154711561478,
+      "grad_norm": 0.39133426547050476,
+      "learning_rate": 9.866740428206935e-06,
+      "loss": 0.291,
+      "step": 262
+    },
+    {
+      "epoch": 0.5036304157025453,
+      "grad_norm": 0.3631567060947418,
+      "learning_rate": 9.864177144913837e-06,
+      "loss": 0.3145,
+      "step": 263
+    },
+    {
+      "epoch": 0.5055453602489428,
+      "grad_norm": 0.3521382212638855,
+      "learning_rate": 9.86158978255926e-06,
+      "loss": 0.3184,
+      "step": 264
+    },
+    {
+      "epoch": 0.5074603047953403,
+      "grad_norm": 0.26583707332611084,
+      "learning_rate": 9.85897835395138e-06,
+      "loss": 0.2197,
+      "step": 265
+    },
+    {
+      "epoch": 0.5093752493417378,
+      "grad_norm": 0.39313459396362305,
+      "learning_rate": 9.856342872017515e-06,
+      "loss": 0.3477,
+      "step": 266
+    },
+    {
+      "epoch": 0.5112901938881353,
+      "grad_norm": 0.3507327139377594,
+      "learning_rate": 9.85368334980405e-06,
+      "loss": 0.332,
+      "step": 267
+    },
+    {
+      "epoch": 0.5132051384345329,
+      "grad_norm": 0.36972326040267944,
+      "learning_rate": 9.85099980047638e-06,
+      "loss": 0.3105,
+      "step": 268
+    },
+    {
+      "epoch": 0.5151200829809304,
+      "grad_norm": 0.44454941153526306,
+      "learning_rate": 9.84829223731883e-06,
+      "loss": 0.3984,
+      "step": 269
+    },
+    {
+      "epoch": 0.5170350275273279,
+      "grad_norm": 0.38550686836242676,
+      "learning_rate": 9.845560673734617e-06,
+      "loss": 0.3789,
+      "step": 270
+    },
+    {
+      "epoch": 0.5189499720737254,
+      "grad_norm": 0.32081368565559387,
+      "learning_rate": 9.842805123245756e-06,
+      "loss": 0.2695,
+      "step": 271
+    },
+    {
+      "epoch": 0.5208649166201229,
+      "grad_norm": 0.365355521440506,
+      "learning_rate": 9.840025599493002e-06,
+      "loss": 0.2871,
+      "step": 272
+    },
+    {
+      "epoch": 0.5227798611665204,
+      "grad_norm": 0.39958202838897705,
+      "learning_rate": 9.837222116235793e-06,
+      "loss": 0.3828,
+      "step": 273
+    },
+    {
+      "epoch": 0.5246948057129179,
+      "grad_norm": 0.40972256660461426,
+      "learning_rate": 9.834394687352168e-06,
+      "loss": 0.4688,
+      "step": 274
+    },
+    {
+      "epoch": 0.5266097502593154,
+      "grad_norm": 0.3923720419406891,
+      "learning_rate": 9.831543326838708e-06,
+      "loss": 0.3008,
+      "step": 275
+    },
+    {
+      "epoch": 0.528524694805713,
+      "grad_norm": 0.40133339166641235,
+      "learning_rate": 9.828668048810452e-06,
+      "loss": 0.3457,
+      "step": 276
+    },
+    {
+      "epoch": 0.5304396393521105,
+      "grad_norm": 0.3792482912540436,
+      "learning_rate": 9.82576886750085e-06,
+      "loss": 0.3438,
+      "step": 277
+    },
+    {
+      "epoch": 0.532354583898508,
+      "grad_norm": 0.37136179208755493,
+      "learning_rate": 9.822845797261676e-06,
+      "loss": 0.3359,
+      "step": 278
+    },
+    {
+      "epoch": 0.5342695284449055,
+      "grad_norm": 0.3462713062763214,
+      "learning_rate": 9.819898852562954e-06,
+      "loss": 0.2578,
+      "step": 279
+    },
+    {
+      "epoch": 0.536184472991303,
+      "grad_norm": 0.47859999537467957,
+      "learning_rate": 9.816928047992904e-06,
+      "loss": 0.3789,
+      "step": 280
+    },
+    {
+      "epoch": 0.5380994175377005,
+      "grad_norm": 0.3499022126197815,
+      "learning_rate": 9.813933398257852e-06,
+      "loss": 0.3047,
+      "step": 281
+    },
+    {
+      "epoch": 0.540014362084098,
+      "grad_norm": 0.3872099816799164,
+      "learning_rate": 9.810914918182168e-06,
+      "loss": 0.3203,
+      "step": 282
+    },
+    {
+      "epoch": 0.5419293066304955,
+      "grad_norm": 0.3496979773044586,
+      "learning_rate": 9.807872622708187e-06,
+      "loss": 0.3008,
+      "step": 283
+    },
+    {
+      "epoch": 0.5438442511768931,
+      "grad_norm": 0.39993637800216675,
+      "learning_rate": 9.804806526896138e-06,
+      "loss": 0.3086,
+      "step": 284
+    },
+    {
+      "epoch": 0.5457591957232905,
+      "grad_norm": 0.3726489245891571,
+      "learning_rate": 9.801716645924066e-06,
+      "loss": 0.2949,
+      "step": 285
+    },
+    {
+      "epoch": 0.547674140269688,
+      "grad_norm": 0.5097160935401917,
+      "learning_rate": 9.798602995087764e-06,
+      "loss": 0.2871,
+      "step": 286
+    },
+    {
+      "epoch": 0.5495890848160855,
+      "grad_norm": 0.4128972291946411,
+      "learning_rate": 9.795465589800688e-06,
+      "loss": 0.3848,
+      "step": 287
+    },
+    {
+      "epoch": 0.551504029362483,
+      "grad_norm": 0.35612717270851135,
+      "learning_rate": 9.79230444559389e-06,
+      "loss": 0.3398,
+      "step": 288
+    },
+    {
+      "epoch": 0.5534189739088805,
+      "grad_norm": 0.34881824254989624,
+      "learning_rate": 9.78911957811593e-06,
+      "loss": 0.3281,
+      "step": 289
+    },
+    {
+      "epoch": 0.555333918455278,
+      "grad_norm": 0.35632357001304626,
+      "learning_rate": 9.785911003132811e-06,
+      "loss": 0.2852,
+      "step": 290
+    },
+    {
+      "epoch": 0.5572488630016755,
+      "grad_norm": 0.37318652868270874,
+      "learning_rate": 9.782678736527892e-06,
+      "loss": 0.2871,
+      "step": 291
+    },
+    {
+      "epoch": 0.559163807548073,
+      "grad_norm": 0.44519978761672974,
+      "learning_rate": 9.779422794301812e-06,
+      "loss": 0.3242,
+      "step": 292
+    },
+    {
+      "epoch": 0.5610787520944706,
+      "grad_norm": 0.35489603877067566,
+      "learning_rate": 9.776143192572414e-06,
+      "loss": 0.332,
+      "step": 293
+    },
+    {
+      "epoch": 0.5629936966408681,
+      "grad_norm": 0.42313477396965027,
+      "learning_rate": 9.772839947574658e-06,
+      "loss": 0.3672,
+      "step": 294
+    },
+    {
+      "epoch": 0.5649086411872656,
+      "grad_norm": 0.35833480954170227,
+      "learning_rate": 9.769513075660548e-06,
+      "loss": 0.3203,
+      "step": 295
+    },
+    {
+      "epoch": 0.5668235857336631,
+      "grad_norm": 0.4363710880279541,
+      "learning_rate": 9.766162593299047e-06,
+      "loss": 0.4043,
+      "step": 296
+    },
+    {
+      "epoch": 0.5687385302800606,
+      "grad_norm": 0.42050284147262573,
+      "learning_rate": 9.762788517075994e-06,
+      "loss": 0.459,
+      "step": 297
+    },
+    {
+      "epoch": 0.5706534748264581,
+      "grad_norm": 0.4468521177768707,
+      "learning_rate": 9.75939086369403e-06,
+      "loss": 0.3867,
+      "step": 298
+    },
+    {
+      "epoch": 0.5725684193728556,
+      "grad_norm": 0.40442460775375366,
+      "learning_rate": 9.755969649972507e-06,
+      "loss": 0.3301,
+      "step": 299
+    },
+    {
+      "epoch": 0.5744833639192531,
+      "grad_norm": 0.39085012674331665,
+      "learning_rate": 9.752524892847402e-06,
+      "loss": 0.3145,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1569,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6708373985367163e+18,
+  "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 sha256:92f794fad9d7d9bdfea957c967fd2ea8d2c222cdb66fb0b670295def8cccff31
+size 7889

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)