Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

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

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

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

latest

@@ -0,0 +1 @@
+global_step423

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d5e5f2d4bcda48455cbda64f3d7214b908a099abf26c009fe12736c3a3bf60
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c3c578b448a961bdbe06d97b5a96540e958a50264a214fb9f80f15917b722c0
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e82ac3f41259912b0979248ab5f536f29c75f4f9f2efd341ec6b199e5ecafd
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8bd69ce548a74e7b6ccd78bcf879ee4a2816dd9920c1f780e91b609ef45d12
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2b44061365f52912ff11ecf42b6814cd5eca26bf785deb15e1b1e5c5b785dd
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3759900e57a0d8a16d713ca14fade334c482ce4ee23d85601d8f5cc898b50cb2
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b98b34c8624255c142ef1c289afeb46d84dfd96034098c99fe5529111f5e33f7
+size 15024

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47949b0df2efc08ab690d6d3675a5d87b18a30a2fb6a1372cc245bf32aa806b4
+size 15024

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a0af955ccdfcc8ba1821a24e8c3dee9ef313357c358ff1e60fc2c2be21e5a4
+size 15024

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3256237cabc84ea9fffa73e0da6d748f96838812078792b22874b902e4bf73
+size 15024

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1a3ba8f11ffd29fde0abe0b3d718b68e1880da2949edbed2a0d7c4fc632903
+size 1064

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,2995 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 423,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0070921985815602835,
+      "grad_norm": 5.777980327606201,
+      "learning_rate": 0.0,
+      "loss": 1.6312,
+      "step": 1
+    },
+    {
+      "epoch": 0.014184397163120567,
+      "grad_norm": 5.754700660705566,
+      "learning_rate": 2.3255813953488374e-07,
+      "loss": 1.65,
+      "step": 2
+    },
+    {
+      "epoch": 0.02127659574468085,
+      "grad_norm": 5.919105529785156,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 1.6812,
+      "step": 3
+    },
+    {
+      "epoch": 0.028368794326241134,
+      "grad_norm": 5.887588977813721,
+      "learning_rate": 6.976744186046513e-07,
+      "loss": 1.7015,
+      "step": 4
+    },
+    {
+      "epoch": 0.03546099290780142,
+      "grad_norm": 5.932762622833252,
+      "learning_rate": 9.30232558139535e-07,
+      "loss": 1.6648,
+      "step": 5
+    },
+    {
+      "epoch": 0.0425531914893617,
+      "grad_norm": 5.459700584411621,
+      "learning_rate": 1.1627906976744188e-06,
+      "loss": 1.6356,
+      "step": 6
+    },
+    {
+      "epoch": 0.04964539007092199,
+      "grad_norm": 5.5110764503479,
+      "learning_rate": 1.3953488372093025e-06,
+      "loss": 1.642,
+      "step": 7
+    },
+    {
+      "epoch": 0.05673758865248227,
+      "grad_norm": 4.986560344696045,
+      "learning_rate": 1.6279069767441862e-06,
+      "loss": 1.6056,
+      "step": 8
+    },
+    {
+      "epoch": 0.06382978723404255,
+      "grad_norm": 4.967083930969238,
+      "learning_rate": 1.86046511627907e-06,
+      "loss": 1.6179,
+      "step": 9
+    },
+    {
+      "epoch": 0.07092198581560284,
+      "grad_norm": 3.372753143310547,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 1.5471,
+      "step": 10
+    },
+    {
+      "epoch": 0.07801418439716312,
+      "grad_norm": 3.3070132732391357,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 1.5119,
+      "step": 11
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 2.9118688106536865,
+      "learning_rate": 2.558139534883721e-06,
+      "loss": 1.4956,
+      "step": 12
+    },
+    {
+      "epoch": 0.09219858156028368,
+      "grad_norm": 2.111111879348755,
+      "learning_rate": 2.790697674418605e-06,
+      "loss": 1.4849,
+      "step": 13
+    },
+    {
+      "epoch": 0.09929078014184398,
+      "grad_norm": 1.896662712097168,
+      "learning_rate": 3.0232558139534885e-06,
+      "loss": 1.4593,
+      "step": 14
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 1.8128881454467773,
+      "learning_rate": 3.2558139534883724e-06,
+      "loss": 1.4569,
+      "step": 15
+    },
+    {
+      "epoch": 0.11347517730496454,
+      "grad_norm": 1.6560497283935547,
+      "learning_rate": 3.4883720930232564e-06,
+      "loss": 1.4258,
+      "step": 16
+    },
+    {
+      "epoch": 0.12056737588652482,
+      "grad_norm": 1.5061492919921875,
+      "learning_rate": 3.72093023255814e-06,
+      "loss": 1.3646,
+      "step": 17
+    },
+    {
+      "epoch": 0.1276595744680851,
+      "grad_norm": 1.4421842098236084,
+      "learning_rate": 3.953488372093024e-06,
+      "loss": 1.3759,
+      "step": 18
+    },
+    {
+      "epoch": 0.1347517730496454,
+      "grad_norm": 1.6656174659729004,
+      "learning_rate": 4.186046511627907e-06,
+      "loss": 1.346,
+      "step": 19
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 1.5938531160354614,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 1.3267,
+      "step": 20
+    },
+    {
+      "epoch": 0.14893617021276595,
+      "grad_norm": 1.4535658359527588,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 1.3159,
+      "step": 21
+    },
+    {
+      "epoch": 0.15602836879432624,
+      "grad_norm": 1.2296608686447144,
+      "learning_rate": 4.883720930232559e-06,
+      "loss": 1.3144,
+      "step": 22
+    },
+    {
+      "epoch": 0.16312056737588654,
+      "grad_norm": 1.0187760591506958,
+      "learning_rate": 5.116279069767442e-06,
+      "loss": 1.2738,
+      "step": 23
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.7561401724815369,
+      "learning_rate": 5.348837209302326e-06,
+      "loss": 1.2752,
+      "step": 24
+    },
+    {
+      "epoch": 0.1773049645390071,
+      "grad_norm": 0.7404045462608337,
+      "learning_rate": 5.58139534883721e-06,
+      "loss": 1.2338,
+      "step": 25
+    },
+    {
+      "epoch": 0.18439716312056736,
+      "grad_norm": 0.8450738787651062,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 1.1847,
+      "step": 26
+    },
+    {
+      "epoch": 0.19148936170212766,
+      "grad_norm": 0.8557640910148621,
+      "learning_rate": 6.046511627906977e-06,
+      "loss": 1.2414,
+      "step": 27
+    },
+    {
+      "epoch": 0.19858156028368795,
+      "grad_norm": 0.7255589365959167,
+      "learning_rate": 6.279069767441861e-06,
+      "loss": 1.1874,
+      "step": 28
+    },
+    {
+      "epoch": 0.20567375886524822,
+      "grad_norm": 0.6485627889633179,
+      "learning_rate": 6.511627906976745e-06,
+      "loss": 1.2164,
+      "step": 29
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.5685610175132751,
+      "learning_rate": 6.744186046511628e-06,
+      "loss": 1.1576,
+      "step": 30
+    },
+    {
+      "epoch": 0.2198581560283688,
+      "grad_norm": 0.5513559579849243,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 1.1599,
+      "step": 31
+    },
+    {
+      "epoch": 0.22695035460992907,
+      "grad_norm": 0.5789648294448853,
+      "learning_rate": 7.209302325581395e-06,
+      "loss": 1.1577,
+      "step": 32
+    },
+    {
+      "epoch": 0.23404255319148937,
+      "grad_norm": 0.5217244625091553,
+      "learning_rate": 7.44186046511628e-06,
+      "loss": 1.1636,
+      "step": 33
+    },
+    {
+      "epoch": 0.24113475177304963,
+      "grad_norm": 0.48746103048324585,
+      "learning_rate": 7.674418604651164e-06,
+      "loss": 1.1309,
+      "step": 34
+    },
+    {
+      "epoch": 0.24822695035460993,
+      "grad_norm": 0.4570249319076538,
+      "learning_rate": 7.906976744186048e-06,
+      "loss": 1.129,
+      "step": 35
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 0.48672929406166077,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 1.1536,
+      "step": 36
+    },
+    {
+      "epoch": 0.2624113475177305,
+      "grad_norm": 0.4759041666984558,
+      "learning_rate": 8.372093023255815e-06,
+      "loss": 1.1194,
+      "step": 37
+    },
+    {
+      "epoch": 0.2695035460992908,
+      "grad_norm": 0.44275835156440735,
+      "learning_rate": 8.604651162790698e-06,
+      "loss": 1.1007,
+      "step": 38
+    },
+    {
+      "epoch": 0.2765957446808511,
+      "grad_norm": 0.4226142466068268,
+      "learning_rate": 8.837209302325582e-06,
+      "loss": 1.1255,
+      "step": 39
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.35801962018013,
+      "learning_rate": 9.069767441860465e-06,
+      "loss": 1.1091,
+      "step": 40
+    },
+    {
+      "epoch": 0.2907801418439716,
+      "grad_norm": 0.33172303438186646,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 1.0927,
+      "step": 41
+    },
+    {
+      "epoch": 0.2978723404255319,
+      "grad_norm": 0.3826102912425995,
+      "learning_rate": 9.534883720930234e-06,
+      "loss": 1.115,
+      "step": 42
+    },
+    {
+      "epoch": 0.3049645390070922,
+      "grad_norm": 0.37179189920425415,
+      "learning_rate": 9.767441860465117e-06,
+      "loss": 1.0644,
+      "step": 43
+    },
+    {
+      "epoch": 0.3120567375886525,
+      "grad_norm": 0.3904111981391907,
+      "learning_rate": 1e-05,
+      "loss": 1.0932,
+      "step": 44
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 0.3148801326751709,
+      "learning_rate": 9.999829128320873e-06,
+      "loss": 1.1085,
+      "step": 45
+    },
+    {
+      "epoch": 0.3262411347517731,
+      "grad_norm": 0.3012698292732239,
+      "learning_rate": 9.999316524962347e-06,
+      "loss": 1.0673,
+      "step": 46
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.2862606346607208,
+      "learning_rate": 9.998462224960176e-06,
+      "loss": 1.0918,
+      "step": 47
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.2962920069694519,
+      "learning_rate": 9.99726628670463e-06,
+      "loss": 1.0914,
+      "step": 48
+    },
+    {
+      "epoch": 0.3475177304964539,
+      "grad_norm": 0.290487140417099,
+      "learning_rate": 9.995728791936505e-06,
+      "loss": 1.086,
+      "step": 49
+    },
+    {
+      "epoch": 0.3546099290780142,
+      "grad_norm": 0.2692384123802185,
+      "learning_rate": 9.993849845741525e-06,
+      "loss": 1.0647,
+      "step": 50
+    },
+    {
+      "epoch": 0.3617021276595745,
+      "grad_norm": 0.2540633976459503,
+      "learning_rate": 9.991629576543164e-06,
+      "loss": 1.0528,
+      "step": 51
+    },
+    {
+      "epoch": 0.36879432624113473,
+      "grad_norm": 0.23808936774730682,
+      "learning_rate": 9.989068136093873e-06,
+      "loss": 1.0747,
+      "step": 52
+    },
+    {
+      "epoch": 0.375886524822695,
+      "grad_norm": 0.24669921398162842,
+      "learning_rate": 9.986165699464706e-06,
+      "loss": 1.051,
+      "step": 53
+    },
+    {
+      "epoch": 0.3829787234042553,
+      "grad_norm": 0.23184196650981903,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 1.0266,
+      "step": 54
+    },
+    {
+      "epoch": 0.3900709219858156,
+      "grad_norm": 0.23330503702163696,
+      "learning_rate": 9.97933865447057e-06,
+      "loss": 1.0789,
+      "step": 55
+    },
+    {
+      "epoch": 0.3971631205673759,
+      "grad_norm": 0.2424897402524948,
+      "learning_rate": 9.975414512725058e-06,
+      "loss": 1.0656,
+      "step": 56
+    },
+    {
+      "epoch": 0.40425531914893614,
+      "grad_norm": 0.21921077370643616,
+      "learning_rate": 9.971150308006689e-06,
+      "loss": 1.0726,
+      "step": 57
+    },
+    {
+      "epoch": 0.41134751773049644,
+      "grad_norm": 0.20950859785079956,
+      "learning_rate": 9.966546331768192e-06,
+      "loss": 1.0632,
+      "step": 58
+    },
+    {
+      "epoch": 0.41843971631205673,
+      "grad_norm": 0.21916094422340393,
+      "learning_rate": 9.961602898685225e-06,
+      "loss": 1.0685,
+      "step": 59
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.20929180085659027,
+      "learning_rate": 9.956320346634877e-06,
+      "loss": 1.0368,
+      "step": 60
+    },
+    {
+      "epoch": 0.4326241134751773,
+      "grad_norm": 0.19803281128406525,
+      "learning_rate": 9.95069903667256e-06,
+      "loss": 1.0454,
+      "step": 61
+    },
+    {
+      "epoch": 0.4397163120567376,
+      "grad_norm": 0.20181335508823395,
+      "learning_rate": 9.944739353007344e-06,
+      "loss": 1.0365,
+      "step": 62
+    },
+    {
+      "epoch": 0.44680851063829785,
+      "grad_norm": 0.2039608657360077,
+      "learning_rate": 9.938441702975689e-06,
+      "loss": 1.0164,
+      "step": 63
+    },
+    {
+      "epoch": 0.45390070921985815,
+      "grad_norm": 0.20605549216270447,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 1.0635,
+      "step": 64
+    },
+    {
+      "epoch": 0.46099290780141844,
+      "grad_norm": 0.1921020895242691,
+      "learning_rate": 9.92483424862726e-06,
+      "loss": 1.032,
+      "step": 65
+    },
+    {
+      "epoch": 0.46808510638297873,
+      "grad_norm": 0.19488710165023804,
+      "learning_rate": 9.917525374361913e-06,
+      "loss": 1.0477,
+      "step": 66
+    },
+    {
+      "epoch": 0.475177304964539,
+      "grad_norm": 0.20245994627475739,
+      "learning_rate": 9.90988039376942e-06,
+      "loss": 1.0539,
+      "step": 67
+    },
+    {
+      "epoch": 0.48226950354609927,
+      "grad_norm": 0.20090186595916748,
+      "learning_rate": 9.901899829374048e-06,
+      "loss": 1.0446,
+      "step": 68
+    },
+    {
+      "epoch": 0.48936170212765956,
+      "grad_norm": 0.20061436295509338,
+      "learning_rate": 9.893584226636773e-06,
+      "loss": 1.0474,
+      "step": 69
+    },
+    {
+      "epoch": 0.49645390070921985,
+      "grad_norm": 0.1957883983850479,
+      "learning_rate": 9.884934153917998e-06,
+      "loss": 1.0212,
+      "step": 70
+    },
+    {
+      "epoch": 0.5035460992907801,
+      "grad_norm": 0.1866292655467987,
+      "learning_rate": 9.8759502024387e-06,
+      "loss": 1.0285,
+      "step": 71
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.20395490527153015,
+      "learning_rate": 9.86663298624003e-06,
+      "loss": 1.05,
+      "step": 72
+    },
+    {
+      "epoch": 0.5177304964539007,
+      "grad_norm": 0.19490036368370056,
+      "learning_rate": 9.856983142141338e-06,
+      "loss": 1.0437,
+      "step": 73
+    },
+    {
+      "epoch": 0.524822695035461,
+      "grad_norm": 0.18446774780750275,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 1.0449,
+      "step": 74
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.20253527164459229,
+      "learning_rate": 9.836688231149593e-06,
+      "loss": 1.0089,
+      "step": 75
+    },
+    {
+      "epoch": 0.5390070921985816,
+      "grad_norm": 0.21082448959350586,
+      "learning_rate": 9.826044551386743e-06,
+      "loss": 1.0228,
+      "step": 76
+    },
+    {
+      "epoch": 0.5460992907801419,
+      "grad_norm": 0.19042915105819702,
+      "learning_rate": 9.81507101788948e-06,
+      "loss": 1.0281,
+      "step": 77
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 0.20652195811271667,
+      "learning_rate": 9.803768380684242e-06,
+      "loss": 1.0584,
+      "step": 78
+    },
+    {
+      "epoch": 0.5602836879432624,
+      "grad_norm": 0.19188715517520905,
+      "learning_rate": 9.792137412291265e-06,
+      "loss": 1.0329,
+      "step": 79
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 0.19346344470977783,
+      "learning_rate": 9.780178907671788e-06,
+      "loss": 1.019,
+      "step": 80
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 0.19410409033298492,
+      "learning_rate": 9.767893684173722e-06,
+      "loss": 1.0201,
+      "step": 81
+    },
+    {
+      "epoch": 0.5815602836879432,
+      "grad_norm": 0.19631166756153107,
+      "learning_rate": 9.755282581475769e-06,
+      "loss": 1.0162,
+      "step": 82
+    },
+    {
+      "epoch": 0.5886524822695035,
+      "grad_norm": 0.18170547485351562,
+      "learning_rate": 9.742346461530048e-06,
+      "loss": 1.0272,
+      "step": 83
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 0.19224867224693298,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 1.002,
+      "step": 84
+    },
+    {
+      "epoch": 0.6028368794326241,
+      "grad_norm": 0.1961982250213623,
+      "learning_rate": 9.715502728715827e-06,
+      "loss": 1.0024,
+      "step": 85
+    },
+    {
+      "epoch": 0.6099290780141844,
+      "grad_norm": 0.19919396936893463,
+      "learning_rate": 9.701596950580807e-06,
+      "loss": 1.0277,
+      "step": 86
+    },
+    {
+      "epoch": 0.6170212765957447,
+      "grad_norm": 0.19481903314590454,
+      "learning_rate": 9.687369824539577e-06,
+      "loss": 1.0318,
+      "step": 87
+    },
+    {
+      "epoch": 0.624113475177305,
+      "grad_norm": 0.20056012272834778,
+      "learning_rate": 9.672822322997305e-06,
+      "loss": 1.0457,
+      "step": 88
+    },
+    {
+      "epoch": 0.6312056737588653,
+      "grad_norm": 0.186695396900177,
+      "learning_rate": 9.657955440256396e-06,
+      "loss": 1.0384,
+      "step": 89
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.1910395473241806,
+      "learning_rate": 9.642770192448537e-06,
+      "loss": 1.02,
+      "step": 90
+    },
+    {
+      "epoch": 0.6453900709219859,
+      "grad_norm": 0.19218654930591583,
+      "learning_rate": 9.627267617465243e-06,
+      "loss": 1.0262,
+      "step": 91
+    },
+    {
+      "epoch": 0.6524822695035462,
+      "grad_norm": 0.20698124170303345,
+      "learning_rate": 9.611448774886925e-06,
+      "loss": 1.0214,
+      "step": 92
+    },
+    {
+      "epoch": 0.6595744680851063,
+      "grad_norm": 0.1869155317544937,
+      "learning_rate": 9.595314745910455e-06,
+      "loss": 1.0176,
+      "step": 93
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19854748249053955,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 1.0213,
+      "step": 94
+    },
+    {
+      "epoch": 0.6737588652482269,
+      "grad_norm": 0.20198820531368256,
+      "learning_rate": 9.562105561188069e-06,
+      "loss": 1.0088,
+      "step": 95
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.19861312210559845,
+      "learning_rate": 9.545032675245814e-06,
+      "loss": 1.0026,
+      "step": 96
+    },
+    {
+      "epoch": 0.6879432624113475,
+      "grad_norm": 0.2025546431541443,
+      "learning_rate": 9.527649142357596e-06,
+      "loss": 0.9929,
+      "step": 97
+    },
+    {
+      "epoch": 0.6950354609929078,
+      "grad_norm": 0.20362333953380585,
+      "learning_rate": 9.509956150664796e-06,
+      "loss": 1.022,
+      "step": 98
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 0.19811417162418365,
+      "learning_rate": 9.491954909459895e-06,
+      "loss": 0.9932,
+      "step": 99
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 0.19115161895751953,
+      "learning_rate": 9.473646649103819e-06,
+      "loss": 1.0015,
+      "step": 100
+    },
+    {
+      "epoch": 0.7163120567375887,
+      "grad_norm": 0.1923169642686844,
+      "learning_rate": 9.45503262094184e-06,
+      "loss": 1.0037,
+      "step": 101
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 0.1964125782251358,
+      "learning_rate": 9.43611409721806e-06,
+      "loss": 1.001,
+      "step": 102
+    },
+    {
+      "epoch": 0.7304964539007093,
+      "grad_norm": 0.19892272353172302,
+      "learning_rate": 9.416892370988445e-06,
+      "loss": 1.0361,
+      "step": 103
+    },
+    {
+      "epoch": 0.7375886524822695,
+      "grad_norm": 0.19403427839279175,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 0.9928,
+      "step": 104
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.19587570428848267,
+      "learning_rate": 9.377544586763216e-06,
+      "loss": 1.0158,
+      "step": 105
+    },
+    {
+      "epoch": 0.75177304964539,
+      "grad_norm": 0.18641604483127594,
+      "learning_rate": 9.357421218136387e-06,
+      "loss": 0.9796,
+      "step": 106
+    },
+    {
+      "epoch": 0.7588652482269503,
+      "grad_norm": 0.1914488524198532,
+      "learning_rate": 9.337000025557477e-06,
+      "loss": 1.0075,
+      "step": 107
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 0.18581831455230713,
+      "learning_rate": 9.31628240478787e-06,
+      "loss": 1.0121,
+      "step": 108
+    },
+    {
+      "epoch": 0.7730496453900709,
+      "grad_norm": 0.19224292039871216,
+      "learning_rate": 9.295269771849426e-06,
+      "loss": 1.0479,
+      "step": 109
+    },
+    {
+      "epoch": 0.7801418439716312,
+      "grad_norm": 0.18176913261413574,
+      "learning_rate": 9.273963562927695e-06,
+      "loss": 1.0063,
+      "step": 110
+    },
+    {
+      "epoch": 0.7872340425531915,
+      "grad_norm": 0.20030972361564636,
+      "learning_rate": 9.252365234273754e-06,
+      "loss": 1.0349,
+      "step": 111
+    },
+    {
+      "epoch": 0.7943262411347518,
+      "grad_norm": 0.18550996482372284,
+      "learning_rate": 9.230476262104678e-06,
+      "loss": 1.0236,
+      "step": 112
+    },
+    {
+      "epoch": 0.8014184397163121,
+      "grad_norm": 0.20744724571704865,
+      "learning_rate": 9.208298142502637e-06,
+      "loss": 0.9884,
+      "step": 113
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 0.1943831443786621,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 1.0071,
+      "step": 114
+    },
+    {
+      "epoch": 0.8156028368794326,
+      "grad_norm": 0.20337262749671936,
+      "learning_rate": 9.163080544038953e-06,
+      "loss": 1.0196,
+      "step": 115
+    },
+    {
+      "epoch": 0.8226950354609929,
+      "grad_norm": 0.20451538264751434,
+      "learning_rate": 9.140044155740102e-06,
+      "loss": 0.9787,
+      "step": 116
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 0.2050030678510666,
+      "learning_rate": 9.11672480092263e-06,
+      "loss": 0.99,
+      "step": 117
+    },
+    {
+      "epoch": 0.8368794326241135,
+      "grad_norm": 0.18984027206897736,
+      "learning_rate": 9.093124073433464e-06,
+      "loss": 1.0012,
+      "step": 118
+    },
+    {
+      "epoch": 0.8439716312056738,
+      "grad_norm": 0.19882577657699585,
+      "learning_rate": 9.069243586350976e-06,
+      "loss": 1.0213,
+      "step": 119
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.18450938165187836,
+      "learning_rate": 9.045084971874738e-06,
+      "loss": 1.025,
+      "step": 120
+    },
+    {
+      "epoch": 0.8581560283687943,
+      "grad_norm": 0.20340915024280548,
+      "learning_rate": 9.02064988121396e-06,
+      "loss": 0.9901,
+      "step": 121
+    },
+    {
+      "epoch": 0.8652482269503546,
+      "grad_norm": 0.20006223022937775,
+      "learning_rate": 8.995939984474624e-06,
+      "loss": 0.9847,
+      "step": 122
+    },
+    {
+      "epoch": 0.8723404255319149,
+      "grad_norm": 0.19546881318092346,
+      "learning_rate": 8.970956970545356e-06,
+      "loss": 1.0009,
+      "step": 123
+    },
+    {
+      "epoch": 0.8794326241134752,
+      "grad_norm": 0.19550330936908722,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 1.0014,
+      "step": 124
+    },
+    {
+      "epoch": 0.8865248226950354,
+      "grad_norm": 0.20895220339298248,
+      "learning_rate": 8.920178439890765e-06,
+      "loss": 0.9941,
+      "step": 125
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 0.19648240506649017,
+      "learning_rate": 8.894386393810563e-06,
+      "loss": 0.9768,
+      "step": 126
+    },
+    {
+      "epoch": 0.900709219858156,
+      "grad_norm": 0.20133382081985474,
+      "learning_rate": 8.868328171593448e-06,
+      "loss": 0.9833,
+      "step": 127
+    },
+    {
+      "epoch": 0.9078014184397163,
+      "grad_norm": 0.21077631413936615,
+      "learning_rate": 8.842005554284296e-06,
+      "loss": 1.0164,
+      "step": 128
+    },
+    {
+      "epoch": 0.9148936170212766,
+      "grad_norm": 0.22325192391872406,
+      "learning_rate": 8.815420340999034e-06,
+      "loss": 1.0162,
+      "step": 129
+    },
+    {
+      "epoch": 0.9219858156028369,
+      "grad_norm": 0.203014075756073,
+      "learning_rate": 8.788574348801676e-06,
+      "loss": 1.015,
+      "step": 130
+    },
+    {
+      "epoch": 0.9290780141843972,
+      "grad_norm": 0.21376149356365204,
+      "learning_rate": 8.761469412580126e-06,
+      "loss": 1.0152,
+      "step": 131
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 0.21650567650794983,
+      "learning_rate": 8.734107384920771e-06,
+      "loss": 0.9946,
+      "step": 132
+    },
+    {
+      "epoch": 0.9432624113475178,
+      "grad_norm": 0.20015230774879456,
+      "learning_rate": 8.706490135981856e-06,
+      "loss": 1.0039,
+      "step": 133
+    },
+    {
+      "epoch": 0.950354609929078,
+      "grad_norm": 0.1983427256345749,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 0.9855,
+      "step": 134
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.200357124209404,
+      "learning_rate": 8.650497541989483e-06,
+      "loss": 1.0297,
+      "step": 135
+    },
+    {
+      "epoch": 0.9645390070921985,
+      "grad_norm": 0.1992904543876648,
+      "learning_rate": 8.622126023955446e-06,
+      "loss": 0.9844,
+      "step": 136
+    },
+    {
+      "epoch": 0.9716312056737588,
+      "grad_norm": 0.2062419056892395,
+      "learning_rate": 8.59350693841912e-06,
+      "loss": 0.9856,
+      "step": 137
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 0.19228526949882507,
+      "learning_rate": 8.564642241456986e-06,
+      "loss": 1.0012,
+      "step": 138
+    },
+    {
+      "epoch": 0.9858156028368794,
+      "grad_norm": 0.1982816457748413,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 1.0048,
+      "step": 139
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 0.21971984207630157,
+      "learning_rate": 8.506183921362443e-06,
+      "loss": 1.0008,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.21237662434577942,
+      "learning_rate": 8.476594293778561e-06,
+      "loss": 0.9844,
+      "step": 141
+    },
+    {
+      "epoch": 1.0070921985815602,
+      "grad_norm": 0.2145996391773224,
+      "learning_rate": 8.446767045592829e-06,
+      "loss": 0.9751,
+      "step": 142
+    },
+    {
+      "epoch": 1.0141843971631206,
+      "grad_norm": 0.18791967630386353,
+      "learning_rate": 8.416704215458042e-06,
+      "loss": 0.9872,
+      "step": 143
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 0.2027330994606018,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 0.9903,
+      "step": 144
+    },
+    {
+      "epoch": 1.0283687943262412,
+      "grad_norm": 0.20994175970554352,
+      "learning_rate": 8.355880044320599e-06,
+      "loss": 0.9883,
+      "step": 145
+    },
+    {
+      "epoch": 1.0354609929078014,
+      "grad_norm": 0.20633184909820557,
+      "learning_rate": 8.325122860569241e-06,
+      "loss": 1.0155,
+      "step": 146
+    },
+    {
+      "epoch": 1.0425531914893618,
+      "grad_norm": 0.2211437076330185,
+      "learning_rate": 8.29413840908729e-06,
+      "loss": 0.9611,
+      "step": 147
+    },
+    {
+      "epoch": 1.049645390070922,
+      "grad_norm": 0.2136813998222351,
+      "learning_rate": 8.262928807620843e-06,
+      "loss": 1.0017,
+      "step": 148
+    },
+    {
+      "epoch": 1.0567375886524824,
+      "grad_norm": 0.20764672756195068,
+      "learning_rate": 8.231496189304704e-06,
+      "loss": 0.9868,
+      "step": 149
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.21529912948608398,
+      "learning_rate": 8.199842702516584e-06,
+      "loss": 0.9791,
+      "step": 150
+    },
+    {
+      "epoch": 1.070921985815603,
+      "grad_norm": 0.21646371483802795,
+      "learning_rate": 8.167970510730254e-06,
+      "loss": 0.9682,
+      "step": 151
+    },
+    {
+      "epoch": 1.0780141843971631,
+      "grad_norm": 0.23525112867355347,
+      "learning_rate": 8.135881792367686e-06,
+      "loss": 0.9728,
+      "step": 152
+    },
+    {
+      "epoch": 1.0851063829787233,
+      "grad_norm": 0.20280921459197998,
+      "learning_rate": 8.103578740650157e-06,
+      "loss": 0.9444,
+      "step": 153
+    },
+    {
+      "epoch": 1.0921985815602837,
+      "grad_norm": 0.22146719694137573,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.9704,
+      "step": 154
+    },
+    {
+      "epoch": 1.099290780141844,
+      "grad_norm": 0.21181389689445496,
+      "learning_rate": 8.038338483131408e-06,
+      "loss": 1.0009,
+      "step": 155
+    },
+    {
+      "epoch": 1.1063829787234043,
+      "grad_norm": 0.19996969401836395,
+      "learning_rate": 8.005405736415127e-06,
+      "loss": 0.9672,
+      "step": 156
+    },
+    {
+      "epoch": 1.1134751773049645,
+      "grad_norm": 0.21428182721138,
+      "learning_rate": 7.972267574208991e-06,
+      "loss": 0.9817,
+      "step": 157
+    },
+    {
+      "epoch": 1.1205673758865249,
+      "grad_norm": 0.20944583415985107,
+      "learning_rate": 7.938926261462366e-06,
+      "loss": 0.9553,
+      "step": 158
+    },
+    {
+      "epoch": 1.127659574468085,
+      "grad_norm": 0.21751722693443298,
+      "learning_rate": 7.905384077009693e-06,
+      "loss": 0.9705,
+      "step": 159
+    },
+    {
+      "epoch": 1.1347517730496455,
+      "grad_norm": 0.19217561185359955,
+      "learning_rate": 7.871643313414718e-06,
+      "loss": 0.9743,
+      "step": 160
+    },
+    {
+      "epoch": 1.1418439716312057,
+      "grad_norm": 0.21539221704006195,
+      "learning_rate": 7.837706276813819e-06,
+      "loss": 0.9742,
+      "step": 161
+    },
+    {
+      "epoch": 1.148936170212766,
+      "grad_norm": 0.20422764122486115,
+      "learning_rate": 7.803575286758365e-06,
+      "loss": 0.9657,
+      "step": 162
+    },
+    {
+      "epoch": 1.1560283687943262,
+      "grad_norm": 0.22533419728279114,
+      "learning_rate": 7.769252676056186e-06,
+      "loss": 0.9888,
+      "step": 163
+    },
+    {
+      "epoch": 1.1631205673758864,
+      "grad_norm": 0.2112210988998413,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 0.9702,
+      "step": 164
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.2327321320772171,
+      "learning_rate": 7.700041989267738e-06,
+      "loss": 0.9968,
+      "step": 165
+    },
+    {
+      "epoch": 1.177304964539007,
+      "grad_norm": 0.20969471335411072,
+      "learning_rate": 7.66515864363997e-06,
+      "loss": 0.9834,
+      "step": 166
+    },
+    {
+      "epoch": 1.1843971631205674,
+      "grad_norm": 0.2076883465051651,
+      "learning_rate": 7.63009313795917e-06,
+      "loss": 1.0022,
+      "step": 167
+    },
+    {
+      "epoch": 1.1914893617021276,
+      "grad_norm": 0.2031002789735794,
+      "learning_rate": 7.594847868906076e-06,
+      "loss": 0.9576,
+      "step": 168
+    },
+    {
+      "epoch": 1.198581560283688,
+      "grad_norm": 0.20676583051681519,
+      "learning_rate": 7.559425245448006e-06,
+      "loss": 0.9522,
+      "step": 169
+    },
+    {
+      "epoch": 1.2056737588652482,
+      "grad_norm": 0.19986094534397125,
+      "learning_rate": 7.52382768867422e-06,
+      "loss": 1.0005,
+      "step": 170
+    },
+    {
+      "epoch": 1.2127659574468086,
+      "grad_norm": 0.20511922240257263,
+      "learning_rate": 7.488057631630438e-06,
+      "loss": 0.9907,
+      "step": 171
+    },
+    {
+      "epoch": 1.2198581560283688,
+      "grad_norm": 0.2091362178325653,
+      "learning_rate": 7.452117519152542e-06,
+      "loss": 0.9696,
+      "step": 172
+    },
+    {
+      "epoch": 1.226950354609929,
+      "grad_norm": 0.20658285915851593,
+      "learning_rate": 7.416009807699481e-06,
+      "loss": 0.9724,
+      "step": 173
+    },
+    {
+      "epoch": 1.2340425531914894,
+      "grad_norm": 0.20578406751155853,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 0.9651,
+      "step": 174
+    },
+    {
+      "epoch": 1.2411347517730495,
+      "grad_norm": 0.19912122189998627,
+      "learning_rate": 7.343301470810809e-06,
+      "loss": 0.9669,
+      "step": 175
+    },
+    {
+      "epoch": 1.24822695035461,
+      "grad_norm": 0.20967933535575867,
+      "learning_rate": 7.30670581489344e-06,
+      "loss": 0.958,
+      "step": 176
+    },
+    {
+      "epoch": 1.2553191489361701,
+      "grad_norm": 0.20045220851898193,
+      "learning_rate": 7.269952498697734e-06,
+      "loss": 0.9891,
+      "step": 177
+    },
+    {
+      "epoch": 1.2624113475177305,
+      "grad_norm": 0.20343008637428284,
+      "learning_rate": 7.233044034264034e-06,
+      "loss": 0.9555,
+      "step": 178
+    },
+    {
+      "epoch": 1.2695035460992907,
+      "grad_norm": 0.2061295509338379,
+      "learning_rate": 7.195982944236853e-06,
+      "loss": 0.9778,
+      "step": 179
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.2172738015651703,
+      "learning_rate": 7.158771761692464e-06,
+      "loss": 0.9904,
+      "step": 180
+    },
+    {
+      "epoch": 1.2836879432624113,
+      "grad_norm": 0.2063237875699997,
+      "learning_rate": 7.121413029965769e-06,
+      "loss": 0.962,
+      "step": 181
+    },
+    {
+      "epoch": 1.2907801418439715,
+      "grad_norm": 0.21524560451507568,
+      "learning_rate": 7.083909302476453e-06,
+      "loss": 0.9384,
+      "step": 182
+    },
+    {
+      "epoch": 1.297872340425532,
+      "grad_norm": 0.2063521295785904,
+      "learning_rate": 7.04626314255447e-06,
+      "loss": 0.9938,
+      "step": 183
+    },
+    {
+      "epoch": 1.3049645390070923,
+      "grad_norm": 0.21301975846290588,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 0.9648,
+      "step": 184
+    },
+    {
+      "epoch": 1.3120567375886525,
+      "grad_norm": 0.22273679077625275,
+      "learning_rate": 6.970553827231809e-06,
+      "loss": 0.9901,
+      "step": 185
+    },
+    {
+      "epoch": 1.3191489361702127,
+      "grad_norm": 0.21703994274139404,
+      "learning_rate": 6.932495846462262e-06,
+      "loss": 0.9551,
+      "step": 186
+    },
+    {
+      "epoch": 1.326241134751773,
+      "grad_norm": 0.20577090978622437,
+      "learning_rate": 6.8943057821686386e-06,
+      "loss": 0.9766,
+      "step": 187
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.2066967487335205,
+      "learning_rate": 6.855986244591104e-06,
+      "loss": 0.957,
+      "step": 188
+    },
+    {
+      "epoch": 1.3404255319148937,
+      "grad_norm": 0.21506328880786896,
+      "learning_rate": 6.817539852819149e-06,
+      "loss": 0.9726,
+      "step": 189
+    },
+    {
+      "epoch": 1.3475177304964538,
+      "grad_norm": 0.20125408470630646,
+      "learning_rate": 6.778969234612583e-06,
+      "loss": 0.9432,
+      "step": 190
+    },
+    {
+      "epoch": 1.3546099290780143,
+      "grad_norm": 0.22270430624485016,
+      "learning_rate": 6.7402770262219234e-06,
+      "loss": 0.9774,
+      "step": 191
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 0.21136341989040375,
+      "learning_rate": 6.701465872208216e-06,
+      "loss": 0.9853,
+      "step": 192
+    },
+    {
+      "epoch": 1.3687943262411348,
+      "grad_norm": 0.1968621164560318,
+      "learning_rate": 6.662538425262285e-06,
+      "loss": 0.9679,
+      "step": 193
+    },
+    {
+      "epoch": 1.375886524822695,
+      "grad_norm": 0.20722901821136475,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 0.9525,
+      "step": 194
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.2028326392173767,
+      "learning_rate": 6.584345302897522e-06,
+      "loss": 0.9623,
+      "step": 195
+    },
+    {
+      "epoch": 1.3900709219858156,
+      "grad_norm": 0.20606288313865662,
+      "learning_rate": 6.545084971874738e-06,
+      "loss": 0.9732,
+      "step": 196
+    },
+    {
+      "epoch": 1.397163120567376,
+      "grad_norm": 0.206637442111969,
+      "learning_rate": 6.505719036346538e-06,
+      "loss": 0.9663,
+      "step": 197
+    },
+    {
+      "epoch": 1.4042553191489362,
+      "grad_norm": 0.20356805622577667,
+      "learning_rate": 6.466250186922325e-06,
+      "loss": 0.9606,
+      "step": 198
+    },
+    {
+      "epoch": 1.4113475177304964,
+      "grad_norm": 0.202161967754364,
+      "learning_rate": 6.426681121245527e-06,
+      "loss": 0.9836,
+      "step": 199
+    },
+    {
+      "epoch": 1.4184397163120568,
+      "grad_norm": 0.20478235185146332,
+      "learning_rate": 6.387014543809224e-06,
+      "loss": 0.9643,
+      "step": 200
+    },
+    {
+      "epoch": 1.425531914893617,
+      "grad_norm": 0.20939572155475616,
+      "learning_rate": 6.34725316577129e-06,
+      "loss": 0.9507,
+      "step": 201
+    },
+    {
+      "epoch": 1.4326241134751774,
+      "grad_norm": 0.2136376053094864,
+      "learning_rate": 6.3073997047691e-06,
+      "loss": 0.9682,
+      "step": 202
+    },
+    {
+      "epoch": 1.4397163120567376,
+      "grad_norm": 0.18985818326473236,
+      "learning_rate": 6.26745688473377e-06,
+      "loss": 0.9759,
+      "step": 203
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 0.21012678742408752,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 0.9834,
+      "step": 204
+    },
+    {
+      "epoch": 1.4539007092198581,
+      "grad_norm": 0.21440032124519348,
+      "learning_rate": 6.187314093639444e-06,
+      "loss": 0.9569,
+      "step": 205
+    },
+    {
+      "epoch": 1.4609929078014185,
+      "grad_norm": 0.21152129769325256,
+      "learning_rate": 6.147119600233758e-06,
+      "loss": 0.9755,
+      "step": 206
+    },
+    {
+      "epoch": 1.4680851063829787,
+      "grad_norm": 0.2023329734802246,
+      "learning_rate": 6.106846702727173e-06,
+      "loss": 0.979,
+      "step": 207
+    },
+    {
+      "epoch": 1.475177304964539,
+      "grad_norm": 0.1883651167154312,
+      "learning_rate": 6.066498153718735e-06,
+      "loss": 0.9468,
+      "step": 208
+    },
+    {
+      "epoch": 1.4822695035460993,
+      "grad_norm": 0.2066640406847,
+      "learning_rate": 6.026076710978172e-06,
+      "loss": 0.9508,
+      "step": 209
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.19015434384346008,
+      "learning_rate": 5.985585137257401e-06,
+      "loss": 0.954,
+      "step": 210
+    },
+    {
+      "epoch": 1.49645390070922,
+      "grad_norm": 0.20339594781398773,
+      "learning_rate": 5.945026200101702e-06,
+      "loss": 0.9522,
+      "step": 211
+    },
+    {
+      "epoch": 1.50354609929078,
+      "grad_norm": 0.20150522887706757,
+      "learning_rate": 5.904402671660551e-06,
+      "loss": 0.9866,
+      "step": 212
+    },
+    {
+      "epoch": 1.5106382978723403,
+      "grad_norm": 0.18772345781326294,
+      "learning_rate": 5.863717328498153e-06,
+      "loss": 0.9712,
+      "step": 213
+    },
+    {
+      "epoch": 1.5177304964539007,
+      "grad_norm": 0.18971088528633118,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 0.9548,
+      "step": 214
+    },
+    {
+      "epoch": 1.524822695035461,
+      "grad_norm": 0.1919199824333191,
+      "learning_rate": 5.782172325201155e-06,
+      "loss": 0.9512,
+      "step": 215
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 0.20227546989917755,
+      "learning_rate": 5.74131823855921e-06,
+      "loss": 0.9716,
+      "step": 216
+    },
+    {
+      "epoch": 1.5390070921985815,
+      "grad_norm": 0.20456035435199738,
+      "learning_rate": 5.70041348380039e-06,
+      "loss": 0.9761,
+      "step": 217
+    },
+    {
+      "epoch": 1.5460992907801419,
+      "grad_norm": 0.198979914188385,
+      "learning_rate": 5.659460856710346e-06,
+      "loss": 0.9662,
+      "step": 218
+    },
+    {
+      "epoch": 1.5531914893617023,
+      "grad_norm": 0.20134767889976501,
+      "learning_rate": 5.61846315634674e-06,
+      "loss": 0.9721,
+      "step": 219
+    },
+    {
+      "epoch": 1.5602836879432624,
+      "grad_norm": 0.21277011930942535,
+      "learning_rate": 5.577423184847932e-06,
+      "loss": 0.9434,
+      "step": 220
+    },
+    {
+      "epoch": 1.5673758865248226,
+      "grad_norm": 0.19326528906822205,
+      "learning_rate": 5.53634374724146e-06,
+      "loss": 0.9436,
+      "step": 221
+    },
+    {
+      "epoch": 1.574468085106383,
+      "grad_norm": 0.18982355296611786,
+      "learning_rate": 5.495227651252315e-06,
+      "loss": 0.9463,
+      "step": 222
+    },
+    {
+      "epoch": 1.5815602836879432,
+      "grad_norm": 0.19490861892700195,
+      "learning_rate": 5.4540777071110415e-06,
+      "loss": 0.967,
+      "step": 223
+    },
+    {
+      "epoch": 1.5886524822695036,
+      "grad_norm": 0.2064967155456543,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 0.9404,
+      "step": 224
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.18899056315422058,
+      "learning_rate": 5.371687526669439e-06,
+      "loss": 0.9714,
+      "step": 225
+    },
+    {
+      "epoch": 1.602836879432624,
+      "grad_norm": 0.2016034871339798,
+      "learning_rate": 5.3304529216284974e-06,
+      "loss": 0.9782,
+      "step": 226
+    },
+    {
+      "epoch": 1.6099290780141844,
+      "grad_norm": 0.19563241302967072,
+      "learning_rate": 5.289195730569321e-06,
+      "loss": 0.9504,
+      "step": 227
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.1931428462266922,
+      "learning_rate": 5.247918773366112e-06,
+      "loss": 0.9631,
+      "step": 228
+    },
+    {
+      "epoch": 1.624113475177305,
+      "grad_norm": 0.18997250497341156,
+      "learning_rate": 5.206624871244066e-06,
+      "loss": 0.9603,
+      "step": 229
+    },
+    {
+      "epoch": 1.6312056737588652,
+      "grad_norm": 0.20812998712062836,
+      "learning_rate": 5.165316846586541e-06,
+      "loss": 0.9441,
+      "step": 230
+    },
+    {
+      "epoch": 1.6382978723404256,
+      "grad_norm": 0.19451972842216492,
+      "learning_rate": 5.123997522742151e-06,
+      "loss": 0.9549,
+      "step": 231
+    },
+    {
+      "epoch": 1.645390070921986,
+      "grad_norm": 0.2104620635509491,
+      "learning_rate": 5.082669723831793e-06,
+      "loss": 0.9516,
+      "step": 232
+    },
+    {
+      "epoch": 1.6524822695035462,
+      "grad_norm": 0.20235127210617065,
+      "learning_rate": 5.041336274555625e-06,
+      "loss": 0.9657,
+      "step": 233
+    },
+    {
+      "epoch": 1.6595744680851063,
+      "grad_norm": 0.21978402137756348,
+      "learning_rate": 5e-06,
+      "loss": 0.9778,
+      "step": 234
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2063991278409958,
+      "learning_rate": 4.958663725444376e-06,
+      "loss": 0.9612,
+      "step": 235
+    },
+    {
+      "epoch": 1.673758865248227,
+      "grad_norm": 0.22222791612148285,
+      "learning_rate": 4.917330276168208e-06,
+      "loss": 0.9505,
+      "step": 236
+    },
+    {
+      "epoch": 1.6808510638297873,
+      "grad_norm": 0.22436769306659698,
+      "learning_rate": 4.87600247725785e-06,
+      "loss": 0.9807,
+      "step": 237
+    },
+    {
+      "epoch": 1.6879432624113475,
+      "grad_norm": 0.20231737196445465,
+      "learning_rate": 4.8346831534134595e-06,
+      "loss": 0.9621,
+      "step": 238
+    },
+    {
+      "epoch": 1.6950354609929077,
+      "grad_norm": 0.1958695352077484,
+      "learning_rate": 4.793375128755934e-06,
+      "loss": 0.9774,
+      "step": 239
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 0.19618870317935944,
+      "learning_rate": 4.752081226633888e-06,
+      "loss": 0.9311,
+      "step": 240
+    },
+    {
+      "epoch": 1.7092198581560285,
+      "grad_norm": 0.19945023953914642,
+      "learning_rate": 4.710804269430681e-06,
+      "loss": 0.931,
+      "step": 241
+    },
+    {
+      "epoch": 1.7163120567375887,
+      "grad_norm": 0.196953684091568,
+      "learning_rate": 4.669547078371503e-06,
+      "loss": 0.9741,
+      "step": 242
+    },
+    {
+      "epoch": 1.7234042553191489,
+      "grad_norm": 0.2063244730234146,
+      "learning_rate": 4.628312473330563e-06,
+      "loss": 0.9726,
+      "step": 243
+    },
+    {
+      "epoch": 1.7304964539007093,
+      "grad_norm": 0.18242137134075165,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 0.9472,
+      "step": 244
+    },
+    {
+      "epoch": 1.7375886524822695,
+      "grad_norm": 0.194502592086792,
+      "learning_rate": 4.545922292888959e-06,
+      "loss": 0.9785,
+      "step": 245
+    },
+    {
+      "epoch": 1.7446808510638299,
+      "grad_norm": 0.20667670667171478,
+      "learning_rate": 4.504772348747687e-06,
+      "loss": 0.9584,
+      "step": 246
+    },
+    {
+      "epoch": 1.75177304964539,
+      "grad_norm": 0.22737909853458405,
+      "learning_rate": 4.463656252758543e-06,
+      "loss": 1.0043,
+      "step": 247
+    },
+    {
+      "epoch": 1.7588652482269502,
+      "grad_norm": 0.20659123361110687,
+      "learning_rate": 4.42257681515207e-06,
+      "loss": 0.9615,
+      "step": 248
+    },
+    {
+      "epoch": 1.7659574468085106,
+      "grad_norm": 0.18234670162200928,
+      "learning_rate": 4.381536843653262e-06,
+      "loss": 0.9551,
+      "step": 249
+    },
+    {
+      "epoch": 1.773049645390071,
+      "grad_norm": 0.2069019377231598,
+      "learning_rate": 4.340539143289655e-06,
+      "loss": 0.9866,
+      "step": 250
+    },
+    {
+      "epoch": 1.7801418439716312,
+      "grad_norm": 0.2130233496427536,
+      "learning_rate": 4.299586516199611e-06,
+      "loss": 0.9544,
+      "step": 251
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.2061052918434143,
+      "learning_rate": 4.25868176144079e-06,
+      "loss": 0.9744,
+      "step": 252
+    },
+    {
+      "epoch": 1.7943262411347518,
+      "grad_norm": 0.19117064774036407,
+      "learning_rate": 4.217827674798845e-06,
+      "loss": 0.9386,
+      "step": 253
+    },
+    {
+      "epoch": 1.8014184397163122,
+      "grad_norm": 0.19266286492347717,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 0.9687,
+      "step": 254
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.18624667823314667,
+      "learning_rate": 4.13628267150185e-06,
+      "loss": 0.9683,
+      "step": 255
+    },
+    {
+      "epoch": 1.8156028368794326,
+      "grad_norm": 0.22691506147384644,
+      "learning_rate": 4.0955973283394525e-06,
+      "loss": 0.9635,
+      "step": 256
+    },
+    {
+      "epoch": 1.8226950354609928,
+      "grad_norm": 0.19554078578948975,
+      "learning_rate": 4.054973799898299e-06,
+      "loss": 0.9584,
+      "step": 257
+    },
+    {
+      "epoch": 1.8297872340425532,
+      "grad_norm": 0.19966286420822144,
+      "learning_rate": 4.0144148627426e-06,
+      "loss": 0.98,
+      "step": 258
+    },
+    {
+      "epoch": 1.8368794326241136,
+      "grad_norm": 0.18636463582515717,
+      "learning_rate": 3.973923289021829e-06,
+      "loss": 0.9292,
+      "step": 259
+    },
+    {
+      "epoch": 1.8439716312056738,
+      "grad_norm": 0.19922591745853424,
+      "learning_rate": 3.9335018462812664e-06,
+      "loss": 0.9495,
+      "step": 260
+    },
+    {
+      "epoch": 1.851063829787234,
+      "grad_norm": 0.1965838074684143,
+      "learning_rate": 3.893153297272829e-06,
+      "loss": 0.9478,
+      "step": 261
+    },
+    {
+      "epoch": 1.8581560283687943,
+      "grad_norm": 0.19277480244636536,
+      "learning_rate": 3.852880399766243e-06,
+      "loss": 0.9529,
+      "step": 262
+    },
+    {
+      "epoch": 1.8652482269503547,
+      "grad_norm": 0.19886280596256256,
+      "learning_rate": 3.8126859063605576e-06,
+      "loss": 0.9703,
+      "step": 263
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 0.19059477746486664,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 0.9379,
+      "step": 264
+    },
+    {
+      "epoch": 1.8794326241134751,
+      "grad_norm": 0.18369245529174805,
+      "learning_rate": 3.73254311526623e-06,
+      "loss": 0.9618,
+      "step": 265
+    },
+    {
+      "epoch": 1.8865248226950353,
+      "grad_norm": 0.19077903032302856,
+      "learning_rate": 3.6926002952309015e-06,
+      "loss": 0.9497,
+      "step": 266
+    },
+    {
+      "epoch": 1.8936170212765957,
+      "grad_norm": 0.19216984510421753,
+      "learning_rate": 3.6527468342287104e-06,
+      "loss": 0.9678,
+      "step": 267
+    },
+    {
+      "epoch": 1.900709219858156,
+      "grad_norm": 0.18526242673397064,
+      "learning_rate": 3.6129854561907786e-06,
+      "loss": 0.9648,
+      "step": 268
+    },
+    {
+      "epoch": 1.9078014184397163,
+      "grad_norm": 0.19354566931724548,
+      "learning_rate": 3.573318878754475e-06,
+      "loss": 0.962,
+      "step": 269
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.19122359156608582,
+      "learning_rate": 3.533749813077677e-06,
+      "loss": 0.9795,
+      "step": 270
+    },
+    {
+      "epoch": 1.9219858156028369,
+      "grad_norm": 0.18988463282585144,
+      "learning_rate": 3.4942809636534637e-06,
+      "loss": 0.9648,
+      "step": 271
+    },
+    {
+      "epoch": 1.9290780141843973,
+      "grad_norm": 0.1826263815164566,
+      "learning_rate": 3.4549150281252635e-06,
+      "loss": 0.9593,
+      "step": 272
+    },
+    {
+      "epoch": 1.9361702127659575,
+      "grad_norm": 0.20058442652225494,
+      "learning_rate": 3.4156546971024783e-06,
+      "loss": 0.9538,
+      "step": 273
+    },
+    {
+      "epoch": 1.9432624113475176,
+      "grad_norm": 0.18569344282150269,
+      "learning_rate": 3.3765026539765832e-06,
+      "loss": 0.9328,
+      "step": 274
+    },
+    {
+      "epoch": 1.950354609929078,
+      "grad_norm": 0.1828421801328659,
+      "learning_rate": 3.3374615747377165e-06,
+      "loss": 0.957,
+      "step": 275
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 0.18512752652168274,
+      "learning_rate": 3.298534127791785e-06,
+      "loss": 0.9555,
+      "step": 276
+    },
+    {
+      "epoch": 1.9645390070921986,
+      "grad_norm": 0.1988511085510254,
+      "learning_rate": 3.259722973778078e-06,
+      "loss": 0.9542,
+      "step": 277
+    },
+    {
+      "epoch": 1.9716312056737588,
+      "grad_norm": 0.20536436140537262,
+      "learning_rate": 3.2210307653874175e-06,
+      "loss": 0.9732,
+      "step": 278
+    },
+    {
+      "epoch": 1.978723404255319,
+      "grad_norm": 0.18166613578796387,
+      "learning_rate": 3.1824601471808504e-06,
+      "loss": 0.9675,
+      "step": 279
+    },
+    {
+      "epoch": 1.9858156028368794,
+      "grad_norm": 0.17907901108264923,
+      "learning_rate": 3.1440137554088957e-06,
+      "loss": 0.9576,
+      "step": 280
+    },
+    {
+      "epoch": 1.9929078014184398,
+      "grad_norm": 0.1949305683374405,
+      "learning_rate": 3.105694217831361e-06,
+      "loss": 0.9552,
+      "step": 281
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2091778814792633,
+      "learning_rate": 3.06750415353774e-06,
+      "loss": 0.9396,
+      "step": 282
+    },
+    {
+      "epoch": 2.00709219858156,
+      "grad_norm": 0.22290584444999695,
+      "learning_rate": 3.0294461727681936e-06,
+      "loss": 0.9482,
+      "step": 283
+    },
+    {
+      "epoch": 2.0141843971631204,
+      "grad_norm": 0.2103525847196579,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 0.9448,
+      "step": 284
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.18519747257232666,
+      "learning_rate": 2.9537368574455304e-06,
+      "loss": 0.9343,
+      "step": 285
+    },
+    {
+      "epoch": 2.028368794326241,
+      "grad_norm": 0.2083410620689392,
+      "learning_rate": 2.9160906975235493e-06,
+      "loss": 0.937,
+      "step": 286
+    },
+    {
+      "epoch": 2.0354609929078014,
+      "grad_norm": 0.21592524647712708,
+      "learning_rate": 2.8785869700342322e-06,
+      "loss": 0.9449,
+      "step": 287
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.18326295912265778,
+      "learning_rate": 2.8412282383075362e-06,
+      "loss": 0.9343,
+      "step": 288
+    },
+    {
+      "epoch": 2.049645390070922,
+      "grad_norm": 0.1971648782491684,
+      "learning_rate": 2.804017055763149e-06,
+      "loss": 0.9498,
+      "step": 289
+    },
+    {
+      "epoch": 2.0567375886524824,
+      "grad_norm": 0.1955241709947586,
+      "learning_rate": 2.766955965735968e-06,
+      "loss": 0.9332,
+      "step": 290
+    },
+    {
+      "epoch": 2.0638297872340425,
+      "grad_norm": 0.18832024931907654,
+      "learning_rate": 2.7300475013022666e-06,
+      "loss": 0.9281,
+      "step": 291
+    },
+    {
+      "epoch": 2.0709219858156027,
+      "grad_norm": 0.18282903730869293,
+      "learning_rate": 2.693294185106562e-06,
+      "loss": 0.9624,
+      "step": 292
+    },
+    {
+      "epoch": 2.078014184397163,
+      "grad_norm": 0.1973196119070053,
+      "learning_rate": 2.6566985291891932e-06,
+      "loss": 0.9235,
+      "step": 293
+    },
+    {
+      "epoch": 2.0851063829787235,
+      "grad_norm": 0.1856066882610321,
+      "learning_rate": 2.6202630348146323e-06,
+      "loss": 0.9416,
+      "step": 294
+    },
+    {
+      "epoch": 2.0921985815602837,
+      "grad_norm": 0.1804654747247696,
+      "learning_rate": 2.5839901923005207e-06,
+      "loss": 0.9279,
+      "step": 295
+    },
+    {
+      "epoch": 2.099290780141844,
+      "grad_norm": 0.1944091022014618,
+      "learning_rate": 2.5478824808474613e-06,
+      "loss": 0.9446,
+      "step": 296
+    },
+    {
+      "epoch": 2.106382978723404,
+      "grad_norm": 0.19213660061359406,
+      "learning_rate": 2.511942368369566e-06,
+      "loss": 0.9423,
+      "step": 297
+    },
+    {
+      "epoch": 2.1134751773049647,
+      "grad_norm": 0.2019748091697693,
+      "learning_rate": 2.476172311325783e-06,
+      "loss": 0.9366,
+      "step": 298
+    },
+    {
+      "epoch": 2.120567375886525,
+      "grad_norm": 0.18752597272396088,
+      "learning_rate": 2.4405747545519966e-06,
+      "loss": 0.943,
+      "step": 299
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.21256884932518005,
+      "learning_rate": 2.4051521310939258e-06,
+      "loss": 0.946,
+      "step": 300
+    },
+    {
+      "epoch": 2.1347517730496453,
+      "grad_norm": 0.19255441427230835,
+      "learning_rate": 2.3699068620408305e-06,
+      "loss": 0.9518,
+      "step": 301
+    },
+    {
+      "epoch": 2.141843971631206,
+      "grad_norm": 0.19296486675739288,
+      "learning_rate": 2.3348413563600324e-06,
+      "loss": 0.9204,
+      "step": 302
+    },
+    {
+      "epoch": 2.148936170212766,
+      "grad_norm": 0.185301274061203,
+      "learning_rate": 2.2999580107322654e-06,
+      "loss": 0.9496,
+      "step": 303
+    },
+    {
+      "epoch": 2.1560283687943262,
+      "grad_norm": 0.18680962920188904,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 0.9317,
+      "step": 304
+    },
+    {
+      "epoch": 2.1631205673758864,
+      "grad_norm": 0.18720752000808716,
+      "learning_rate": 2.2307473239438153e-06,
+      "loss": 0.9442,
+      "step": 305
+    },
+    {
+      "epoch": 2.1702127659574466,
+      "grad_norm": 0.17528828978538513,
+      "learning_rate": 2.1964247132416373e-06,
+      "loss": 0.911,
+      "step": 306
+    },
+    {
+      "epoch": 2.1773049645390072,
+      "grad_norm": 0.20737330615520477,
+      "learning_rate": 2.1622937231861823e-06,
+      "loss": 0.9548,
+      "step": 307
+    },
+    {
+      "epoch": 2.1843971631205674,
+      "grad_norm": 0.19633513689041138,
+      "learning_rate": 2.1283566865852824e-06,
+      "loss": 0.9262,
+      "step": 308
+    },
+    {
+      "epoch": 2.1914893617021276,
+      "grad_norm": 0.1804002970457077,
+      "learning_rate": 2.094615922990309e-06,
+      "loss": 0.9323,
+      "step": 309
+    },
+    {
+      "epoch": 2.198581560283688,
+      "grad_norm": 0.19144874811172485,
+      "learning_rate": 2.061073738537635e-06,
+      "loss": 0.9455,
+      "step": 310
+    },
+    {
+      "epoch": 2.2056737588652484,
+      "grad_norm": 0.1808236688375473,
+      "learning_rate": 2.027732425791011e-06,
+      "loss": 0.9518,
+      "step": 311
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 0.1889459639787674,
+      "learning_rate": 1.9945942635848745e-06,
+      "loss": 0.9645,
+      "step": 312
+    },
+    {
+      "epoch": 2.219858156028369,
+      "grad_norm": 0.18562434613704681,
+      "learning_rate": 1.961661516868594e-06,
+      "loss": 0.9139,
+      "step": 313
+    },
+    {
+      "epoch": 2.226950354609929,
+      "grad_norm": 0.19447514414787292,
+      "learning_rate": 1.928936436551661e-06,
+      "loss": 0.9423,
+      "step": 314
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "grad_norm": 0.18953830003738403,
+      "learning_rate": 1.8964212593498444e-06,
+      "loss": 0.9662,
+      "step": 315
+    },
+    {
+      "epoch": 2.2411347517730498,
+      "grad_norm": 0.18533062934875488,
+      "learning_rate": 1.864118207632315e-06,
+      "loss": 0.9559,
+      "step": 316
+    },
+    {
+      "epoch": 2.24822695035461,
+      "grad_norm": 0.18788859248161316,
+      "learning_rate": 1.8320294892697477e-06,
+      "loss": 0.9379,
+      "step": 317
+    },
+    {
+      "epoch": 2.25531914893617,
+      "grad_norm": 0.18943147361278534,
+      "learning_rate": 1.8001572974834169e-06,
+      "loss": 0.9275,
+      "step": 318
+    },
+    {
+      "epoch": 2.2624113475177303,
+      "grad_norm": 0.17720432579517365,
+      "learning_rate": 1.7685038106952952e-06,
+      "loss": 0.9148,
+      "step": 319
+    },
+    {
+      "epoch": 2.269503546099291,
+      "grad_norm": 0.17993542551994324,
+      "learning_rate": 1.7370711923791567e-06,
+      "loss": 0.9403,
+      "step": 320
+    },
+    {
+      "epoch": 2.276595744680851,
+      "grad_norm": 0.1805652678012848,
+      "learning_rate": 1.7058615909127102e-06,
+      "loss": 0.9404,
+      "step": 321
+    },
+    {
+      "epoch": 2.2836879432624113,
+      "grad_norm": 0.1839425414800644,
+      "learning_rate": 1.6748771394307584e-06,
+      "loss": 0.949,
+      "step": 322
+    },
+    {
+      "epoch": 2.2907801418439715,
+      "grad_norm": 0.18259738385677338,
+      "learning_rate": 1.6441199556794036e-06,
+      "loss": 0.9494,
+      "step": 323
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 0.1737503856420517,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 0.941,
+      "step": 324
+    },
+    {
+      "epoch": 2.3049645390070923,
+      "grad_norm": 0.18038944900035858,
+      "learning_rate": 1.5832957845419583e-06,
+      "loss": 0.9294,
+      "step": 325
+    },
+    {
+      "epoch": 2.3120567375886525,
+      "grad_norm": 0.18109843134880066,
+      "learning_rate": 1.5532329544071712e-06,
+      "loss": 0.9169,
+      "step": 326
+    },
+    {
+      "epoch": 2.3191489361702127,
+      "grad_norm": 0.18001320958137512,
+      "learning_rate": 1.5234057062214403e-06,
+      "loss": 0.8874,
+      "step": 327
+    },
+    {
+      "epoch": 2.326241134751773,
+      "grad_norm": 0.1792004108428955,
+      "learning_rate": 1.4938160786375571e-06,
+      "loss": 0.9449,
+      "step": 328
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.17555391788482666,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 0.9435,
+      "step": 329
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.17382599413394928,
+      "learning_rate": 1.4353577585430152e-06,
+      "loss": 0.9263,
+      "step": 330
+    },
+    {
+      "epoch": 2.347517730496454,
+      "grad_norm": 0.17780086398124695,
+      "learning_rate": 1.406493061580881e-06,
+      "loss": 0.9481,
+      "step": 331
+    },
+    {
+      "epoch": 2.354609929078014,
+      "grad_norm": 0.18043147027492523,
+      "learning_rate": 1.3778739760445552e-06,
+      "loss": 0.9431,
+      "step": 332
+    },
+    {
+      "epoch": 2.3617021276595747,
+      "grad_norm": 0.19360171258449554,
+      "learning_rate": 1.3495024580105193e-06,
+      "loss": 0.9468,
+      "step": 333
+    },
+    {
+      "epoch": 2.368794326241135,
+      "grad_norm": 0.18124336004257202,
+      "learning_rate": 1.321380446634342e-06,
+      "loss": 0.9493,
+      "step": 334
+    },
+    {
+      "epoch": 2.375886524822695,
+      "grad_norm": 0.16850939393043518,
+      "learning_rate": 1.293509864018146e-06,
+      "loss": 0.9452,
+      "step": 335
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 0.17136213183403015,
+      "learning_rate": 1.2658926150792321e-06,
+      "loss": 0.9308,
+      "step": 336
+    },
+    {
+      "epoch": 2.3900709219858154,
+      "grad_norm": 0.19403225183486938,
+      "learning_rate": 1.2385305874198778e-06,
+      "loss": 0.9544,
+      "step": 337
+    },
+    {
+      "epoch": 2.397163120567376,
+      "grad_norm": 0.1776721477508545,
+      "learning_rate": 1.2114256511983274e-06,
+      "loss": 0.9473,
+      "step": 338
+    },
+    {
+      "epoch": 2.404255319148936,
+      "grad_norm": 0.17469924688339233,
+      "learning_rate": 1.1845796590009684e-06,
+      "loss": 0.9388,
+      "step": 339
+    },
+    {
+      "epoch": 2.4113475177304964,
+      "grad_norm": 0.17591865360736847,
+      "learning_rate": 1.157994445715706e-06,
+      "loss": 0.9247,
+      "step": 340
+    },
+    {
+      "epoch": 2.4184397163120566,
+      "grad_norm": 0.17730483412742615,
+      "learning_rate": 1.1316718284065536e-06,
+      "loss": 0.9471,
+      "step": 341
+    },
+    {
+      "epoch": 2.425531914893617,
+      "grad_norm": 0.1710953712463379,
+      "learning_rate": 1.1056136061894386e-06,
+      "loss": 0.9319,
+      "step": 342
+    },
+    {
+      "epoch": 2.4326241134751774,
+      "grad_norm": 0.1860751360654831,
+      "learning_rate": 1.0798215601092354e-06,
+      "loss": 0.9283,
+      "step": 343
+    },
+    {
+      "epoch": 2.4397163120567376,
+      "grad_norm": 0.17981447279453278,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 0.9358,
+      "step": 344
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 0.17886151373386383,
+      "learning_rate": 1.0290430294546449e-06,
+      "loss": 0.957,
+      "step": 345
+    },
+    {
+      "epoch": 2.453900709219858,
+      "grad_norm": 0.18198616802692413,
+      "learning_rate": 1.0040600155253766e-06,
+      "loss": 0.9383,
+      "step": 346
+    },
+    {
+      "epoch": 2.4609929078014185,
+      "grad_norm": 0.1727137714624405,
+      "learning_rate": 9.793501187860432e-07,
+      "loss": 0.9405,
+      "step": 347
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 0.1783406287431717,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.925,
+      "step": 348
+    },
+    {
+      "epoch": 2.475177304964539,
+      "grad_norm": 0.1867266297340393,
+      "learning_rate": 9.307564136490255e-07,
+      "loss": 0.9561,
+      "step": 349
+    },
+    {
+      "epoch": 2.482269503546099,
+      "grad_norm": 0.1743844449520111,
+      "learning_rate": 9.068759265665384e-07,
+      "loss": 0.9438,
+      "step": 350
+    },
+    {
+      "epoch": 2.4893617021276597,
+      "grad_norm": 0.18149304389953613,
+      "learning_rate": 8.832751990773714e-07,
+      "loss": 0.9382,
+      "step": 351
+    },
+    {
+      "epoch": 2.49645390070922,
+      "grad_norm": 0.17251861095428467,
+      "learning_rate": 8.599558442598998e-07,
+      "loss": 0.9511,
+      "step": 352
+    },
+    {
+      "epoch": 2.50354609929078,
+      "grad_norm": 0.18050801753997803,
+      "learning_rate": 8.369194559610483e-07,
+      "loss": 0.9428,
+      "step": 353
+    },
+    {
+      "epoch": 2.5106382978723403,
+      "grad_norm": 0.17342498898506165,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 0.9181,
+      "step": 354
+    },
+    {
+      "epoch": 2.5177304964539005,
+      "grad_norm": 0.17598570883274078,
+      "learning_rate": 7.917018574973646e-07,
+      "loss": 0.9198,
+      "step": 355
+    },
+    {
+      "epoch": 2.524822695035461,
+      "grad_norm": 0.1778562217950821,
+      "learning_rate": 7.695237378953224e-07,
+      "loss": 0.9202,
+      "step": 356
+    },
+    {
+      "epoch": 2.5319148936170213,
+      "grad_norm": 0.18783792853355408,
+      "learning_rate": 7.476347657262456e-07,
+      "loss": 0.9768,
+      "step": 357
+    },
+    {
+      "epoch": 2.5390070921985815,
+      "grad_norm": 0.17972299456596375,
+      "learning_rate": 7.260364370723044e-07,
+      "loss": 0.9188,
+      "step": 358
+    },
+    {
+      "epoch": 2.546099290780142,
+      "grad_norm": 0.17691974341869354,
+      "learning_rate": 7.047302281505735e-07,
+      "loss": 0.9454,
+      "step": 359
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.17989806830883026,
+      "learning_rate": 6.837175952121305e-07,
+      "loss": 0.912,
+      "step": 360
+    },
+    {
+      "epoch": 2.5602836879432624,
+      "grad_norm": 0.1767599880695343,
+      "learning_rate": 6.629999744425236e-07,
+      "loss": 0.9118,
+      "step": 361
+    },
+    {
+      "epoch": 2.5673758865248226,
+      "grad_norm": 0.17483338713645935,
+      "learning_rate": 6.425787818636131e-07,
+      "loss": 0.9418,
+      "step": 362
+    },
+    {
+      "epoch": 2.574468085106383,
+      "grad_norm": 0.17281189560890198,
+      "learning_rate": 6.224554132367861e-07,
+      "loss": 0.931,
+      "step": 363
+    },
+    {
+      "epoch": 2.581560283687943,
+      "grad_norm": 0.17162910103797913,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 0.929,
+      "step": 364
+    },
+    {
+      "epoch": 2.5886524822695036,
+      "grad_norm": 0.17338411509990692,
+      "learning_rate": 5.831076290115572e-07,
+      "loss": 0.9427,
+      "step": 365
+    },
+    {
+      "epoch": 2.595744680851064,
+      "grad_norm": 0.17692013084888458,
+      "learning_rate": 5.63885902781941e-07,
+      "loss": 0.9449,
+      "step": 366
+    },
+    {
+      "epoch": 2.602836879432624,
+      "grad_norm": 0.1654009222984314,
+      "learning_rate": 5.449673790581611e-07,
+      "loss": 0.9613,
+      "step": 367
+    },
+    {
+      "epoch": 2.6099290780141846,
+      "grad_norm": 0.20816448330879211,
+      "learning_rate": 5.263533508961827e-07,
+      "loss": 0.958,
+      "step": 368
+    },
+    {
+      "epoch": 2.617021276595745,
+      "grad_norm": 0.17404668033123016,
+      "learning_rate": 5.080450905401057e-07,
+      "loss": 0.9497,
+      "step": 369
+    },
+    {
+      "epoch": 2.624113475177305,
+      "grad_norm": 0.17764751613140106,
+      "learning_rate": 4.900438493352056e-07,
+      "loss": 0.9436,
+      "step": 370
+    },
+    {
+      "epoch": 2.631205673758865,
+      "grad_norm": 0.16908040642738342,
+      "learning_rate": 4.723508576424063e-07,
+      "loss": 0.9346,
+      "step": 371
+    },
+    {
+      "epoch": 2.6382978723404253,
+      "grad_norm": 0.17620623111724854,
+      "learning_rate": 4.549673247541875e-07,
+      "loss": 0.9394,
+      "step": 372
+    },
+    {
+      "epoch": 2.645390070921986,
+      "grad_norm": 0.17822693288326263,
+      "learning_rate": 4.3789443881193107e-07,
+      "loss": 0.9469,
+      "step": 373
+    },
+    {
+      "epoch": 2.652482269503546,
+      "grad_norm": 0.17219433188438416,
+      "learning_rate": 4.211333667247125e-07,
+      "loss": 0.9541,
+      "step": 374
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.17476940155029297,
+      "learning_rate": 4.046852540895446e-07,
+      "loss": 0.9304,
+      "step": 375
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.16585884988307953,
+      "learning_rate": 3.885512251130763e-07,
+      "loss": 0.9144,
+      "step": 376
+    },
+    {
+      "epoch": 2.673758865248227,
+      "grad_norm": 0.17504124343395233,
+      "learning_rate": 3.7273238253475783e-07,
+      "loss": 0.9349,
+      "step": 377
+    },
+    {
+      "epoch": 2.6808510638297873,
+      "grad_norm": 0.17808987200260162,
+      "learning_rate": 3.572298075514652e-07,
+      "loss": 0.9283,
+      "step": 378
+    },
+    {
+      "epoch": 2.6879432624113475,
+      "grad_norm": 0.17109963297843933,
+      "learning_rate": 3.420445597436056e-07,
+      "loss": 0.923,
+      "step": 379
+    },
+    {
+      "epoch": 2.6950354609929077,
+      "grad_norm": 0.16899849474430084,
+      "learning_rate": 3.271776770026963e-07,
+      "loss": 0.9479,
+      "step": 380
+    },
+    {
+      "epoch": 2.702127659574468,
+      "grad_norm": 0.16950707137584686,
+      "learning_rate": 3.126301754604233e-07,
+      "loss": 0.9423,
+      "step": 381
+    },
+    {
+      "epoch": 2.7092198581560285,
+      "grad_norm": 0.16774339973926544,
+      "learning_rate": 2.984030494191942e-07,
+      "loss": 0.9665,
+      "step": 382
+    },
+    {
+      "epoch": 2.7163120567375887,
+      "grad_norm": 0.17978820204734802,
+      "learning_rate": 2.844972712841737e-07,
+      "loss": 0.9649,
+      "step": 383
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 0.17238686978816986,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 0.9391,
+      "step": 384
+    },
+    {
+      "epoch": 2.7304964539007095,
+      "grad_norm": 0.17088578641414642,
+      "learning_rate": 2.57653538469953e-07,
+      "loss": 0.941,
+      "step": 385
+    },
+    {
+      "epoch": 2.7375886524822697,
+      "grad_norm": 0.1665761023759842,
+      "learning_rate": 2.447174185242324e-07,
+      "loss": 0.9552,
+      "step": 386
+    },
+    {
+      "epoch": 2.74468085106383,
+      "grad_norm": 0.17608121037483215,
+      "learning_rate": 2.321063158262793e-07,
+      "loss": 0.9385,
+      "step": 387
+    },
+    {
+      "epoch": 2.75177304964539,
+      "grad_norm": 0.1641273945569992,
+      "learning_rate": 2.198210923282118e-07,
+      "loss": 0.926,
+      "step": 388
+    },
+    {
+      "epoch": 2.7588652482269502,
+      "grad_norm": 0.17171336710453033,
+      "learning_rate": 2.0786258770873647e-07,
+      "loss": 0.932,
+      "step": 389
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.16748470067977905,
+      "learning_rate": 1.962316193157593e-07,
+      "loss": 0.9418,
+      "step": 390
+    },
+    {
+      "epoch": 2.773049645390071,
+      "grad_norm": 0.16219119727611542,
+      "learning_rate": 1.849289821105199e-07,
+      "loss": 0.9365,
+      "step": 391
+    },
+    {
+      "epoch": 2.780141843971631,
+      "grad_norm": 0.1692589968442917,
+      "learning_rate": 1.7395544861325718e-07,
+      "loss": 0.9338,
+      "step": 392
+    },
+    {
+      "epoch": 2.7872340425531914,
+      "grad_norm": 0.17481659352779388,
+      "learning_rate": 1.6331176885040878e-07,
+      "loss": 0.9732,
+      "step": 393
+    },
+    {
+      "epoch": 2.794326241134752,
+      "grad_norm": 0.16948547959327698,
+      "learning_rate": 1.5299867030334815e-07,
+      "loss": 0.9352,
+      "step": 394
+    },
+    {
+      "epoch": 2.801418439716312,
+      "grad_norm": 0.17257732152938843,
+      "learning_rate": 1.4301685785866215e-07,
+      "loss": 0.961,
+      "step": 395
+    },
+    {
+      "epoch": 2.8085106382978724,
+      "grad_norm": 0.1700429916381836,
+      "learning_rate": 1.333670137599713e-07,
+      "loss": 0.9465,
+      "step": 396
+    },
+    {
+      "epoch": 2.8156028368794326,
+      "grad_norm": 0.16693882644176483,
+      "learning_rate": 1.2404979756130142e-07,
+      "loss": 0.9416,
+      "step": 397
+    },
+    {
+      "epoch": 2.8226950354609928,
+      "grad_norm": 0.16439220309257507,
+      "learning_rate": 1.1506584608200366e-07,
+      "loss": 0.9226,
+      "step": 398
+    },
+    {
+      "epoch": 2.829787234042553,
+      "grad_norm": 0.1747705340385437,
+      "learning_rate": 1.0641577336322761e-07,
+      "loss": 0.9604,
+      "step": 399
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "grad_norm": 0.16952365636825562,
+      "learning_rate": 9.810017062595322e-08,
+      "loss": 0.9352,
+      "step": 400
+    },
+    {
+      "epoch": 2.8439716312056738,
+      "grad_norm": 0.1762147843837738,
+      "learning_rate": 9.011960623058202e-08,
+      "loss": 0.9526,
+      "step": 401
+    },
+    {
+      "epoch": 2.851063829787234,
+      "grad_norm": 0.1663467288017273,
+      "learning_rate": 8.247462563808816e-08,
+      "loss": 0.9287,
+      "step": 402
+    },
+    {
+      "epoch": 2.8581560283687946,
+      "grad_norm": 0.1643829047679901,
+      "learning_rate": 7.516575137274162e-08,
+      "loss": 0.9366,
+      "step": 403
+    },
+    {
+      "epoch": 2.8652482269503547,
+      "grad_norm": 0.16540059447288513,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 0.957,
+      "step": 404
+    },
+    {
+      "epoch": 2.872340425531915,
+      "grad_norm": 0.1641610562801361,
+      "learning_rate": 6.15582970243117e-08,
+      "loss": 0.9502,
+      "step": 405
+    },
+    {
+      "epoch": 2.879432624113475,
+      "grad_norm": 0.16954517364501953,
+      "learning_rate": 5.526064699265754e-08,
+      "loss": 0.9474,
+      "step": 406
+    },
+    {
+      "epoch": 2.8865248226950353,
+      "grad_norm": 0.17791299521923065,
+      "learning_rate": 4.930096332744105e-08,
+      "loss": 0.9531,
+      "step": 407
+    },
+    {
+      "epoch": 2.8936170212765955,
+      "grad_norm": 0.1743258535861969,
+      "learning_rate": 4.367965336512403e-08,
+      "loss": 0.965,
+      "step": 408
+    },
+    {
+      "epoch": 2.900709219858156,
+      "grad_norm": 0.16537080705165863,
+      "learning_rate": 3.839710131477492e-08,
+      "loss": 0.9288,
+      "step": 409
+    },
+    {
+      "epoch": 2.9078014184397163,
+      "grad_norm": 0.17257335782051086,
+      "learning_rate": 3.345366823180929e-08,
+      "loss": 0.9151,
+      "step": 410
+    },
+    {
+      "epoch": 2.9148936170212765,
+      "grad_norm": 0.16965629160404205,
+      "learning_rate": 2.884969199331178e-08,
+      "loss": 0.8977,
+      "step": 411
+    },
+    {
+      "epoch": 2.921985815602837,
+      "grad_norm": 0.16547615826129913,
+      "learning_rate": 2.4585487274942922e-08,
+      "loss": 0.9456,
+      "step": 412
+    },
+    {
+      "epoch": 2.9290780141843973,
+      "grad_norm": 0.1668514609336853,
+      "learning_rate": 2.0661345529430777e-08,
+      "loss": 0.9371,
+      "step": 413
+    },
+    {
+      "epoch": 2.9361702127659575,
+      "grad_norm": 0.175437793135643,
+      "learning_rate": 1.7077534966650767e-08,
+      "loss": 0.9365,
+      "step": 414
+    },
+    {
+      "epoch": 2.9432624113475176,
+      "grad_norm": 0.16184265911579132,
+      "learning_rate": 1.383430053529422e-08,
+      "loss": 0.9164,
+      "step": 415
+    },
+    {
+      "epoch": 2.950354609929078,
+      "grad_norm": 0.17287677526474,
+      "learning_rate": 1.0931863906127327e-08,
+      "loss": 0.9402,
+      "step": 416
+    },
+    {
+      "epoch": 2.9574468085106385,
+      "grad_norm": 0.16356982290744781,
+      "learning_rate": 8.37042345683714e-09,
+      "loss": 0.9708,
+      "step": 417
+    },
+    {
+      "epoch": 2.9645390070921986,
+      "grad_norm": 0.16705556213855743,
+      "learning_rate": 6.150154258476315e-09,
+      "loss": 0.9498,
+      "step": 418
+    },
+    {
+      "epoch": 2.971631205673759,
+      "grad_norm": 0.1613406389951706,
+      "learning_rate": 4.2712080634949024e-09,
+      "loss": 0.9287,
+      "step": 419
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 0.1684153974056244,
+      "learning_rate": 2.7337132953697555e-09,
+      "loss": 0.9274,
+      "step": 420
+    },
+    {
+      "epoch": 2.9858156028368796,
+      "grad_norm": 0.16626179218292236,
+      "learning_rate": 1.53777503982655e-09,
+      "loss": 0.9243,
+      "step": 421
+    },
+    {
+      "epoch": 2.99290780141844,
+      "grad_norm": 0.17238499224185944,
+      "learning_rate": 6.834750376549793e-10,
+      "loss": 0.9477,
+      "step": 422
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.16570501029491425,
+      "learning_rate": 1.7087167912710477e-10,
+      "loss": 0.9324,
+      "step": 423
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 423,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2261545899786240.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810e0b0f68ae49671684020f373cd047296dd4f8f9f1464d80c2484ee310f1e0
+size 7736

zero_to_fp32.py

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