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_step428

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68dd19a0a06811b70365c860aa2e0da5d48f6152abc53453f12c2526b5015e2a
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecaeaf1da96587842b538ed8a0e024bdcc144698ccdcd7c38e3f3cd8c00337d0
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f5d1769df0fb4cead2b686f37b4309e76ac58dfd4bb97b12502ed0a5a14ba48
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:445f8cb83634c9e876afbbd7edbea8d75cfadca55fc0db0d65588b48ca9af38c
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e65afd1dc38ed83186eed0ee9ad1ff2639702b7748b3c3dc962ef9a730e379
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e250a7ca996b5b1959d8175f6fa129f338ba5f39815e33bd9041a394cead461d
+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 sha256:39a860bb18ec0809d2beed844f22fd57e57b50458132796070d6fbbf3893e1cc
+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 +1,3037 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 429,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006996064713598601,
+      "grad_norm": 5.937824249267578,
+      "learning_rate": 0.0,
+      "loss": 1.7117,
+      "step": 1
+    },
+    {
+      "epoch": 0.013992129427197202,
+      "grad_norm": 6.1023173332214355,
+      "learning_rate": 2.3255813953488374e-07,
+      "loss": 1.7574,
+      "step": 2
+    },
+    {
+      "epoch": 0.020988194140795804,
+      "grad_norm": 5.9199066162109375,
+      "learning_rate": 4.651162790697675e-07,
+      "loss": 1.7173,
+      "step": 3
+    },
+    {
+      "epoch": 0.027984258854394404,
+      "grad_norm": 6.086047649383545,
+      "learning_rate": 6.976744186046513e-07,
+      "loss": 1.7361,
+      "step": 4
+    },
+    {
+      "epoch": 0.034980323567993,
+      "grad_norm": 5.97832727432251,
+      "learning_rate": 9.30232558139535e-07,
+      "loss": 1.7116,
+      "step": 5
+    },
+    {
+      "epoch": 0.04197638828159161,
+      "grad_norm": 5.771295547485352,
+      "learning_rate": 1.1627906976744188e-06,
+      "loss": 1.7151,
+      "step": 6
+    },
+    {
+      "epoch": 0.04897245299519021,
+      "grad_norm": 5.788296222686768,
+      "learning_rate": 1.3953488372093025e-06,
+      "loss": 1.7371,
+      "step": 7
+    },
+    {
+      "epoch": 0.05596851770878881,
+      "grad_norm": 5.347567081451416,
+      "learning_rate": 1.6279069767441862e-06,
+      "loss": 1.7255,
+      "step": 8
+    },
+    {
+      "epoch": 0.06296458242238741,
+      "grad_norm": 5.00020170211792,
+      "learning_rate": 1.86046511627907e-06,
+      "loss": 1.6789,
+      "step": 9
+    },
+    {
+      "epoch": 0.069960647135986,
+      "grad_norm": 3.755484104156494,
+      "learning_rate": 2.0930232558139536e-06,
+      "loss": 1.6309,
+      "step": 10
+    },
+    {
+      "epoch": 0.07695671184958461,
+      "grad_norm": 3.554680347442627,
+      "learning_rate": 2.3255813953488376e-06,
+      "loss": 1.5802,
+      "step": 11
+    },
+    {
+      "epoch": 0.08395277656318322,
+      "grad_norm": 3.4229071140289307,
+      "learning_rate": 2.558139534883721e-06,
+      "loss": 1.6369,
+      "step": 12
+    },
+    {
+      "epoch": 0.09094884127678181,
+      "grad_norm": 2.332273244857788,
+      "learning_rate": 2.790697674418605e-06,
+      "loss": 1.5343,
+      "step": 13
+    },
+    {
+      "epoch": 0.09794490599038042,
+      "grad_norm": 2.1997501850128174,
+      "learning_rate": 3.0232558139534885e-06,
+      "loss": 1.5487,
+      "step": 14
+    },
+    {
+      "epoch": 0.10494097070397901,
+      "grad_norm": 2.141204595565796,
+      "learning_rate": 3.2558139534883724e-06,
+      "loss": 1.5495,
+      "step": 15
+    },
+    {
+      "epoch": 0.11193703541757762,
+      "grad_norm": 1.8256744146347046,
+      "learning_rate": 3.4883720930232564e-06,
+      "loss": 1.5049,
+      "step": 16
+    },
+    {
+      "epoch": 0.11893310013117621,
+      "grad_norm": 1.7434165477752686,
+      "learning_rate": 3.72093023255814e-06,
+      "loss": 1.5033,
+      "step": 17
+    },
+    {
+      "epoch": 0.12592916484477482,
+      "grad_norm": 1.5808353424072266,
+      "learning_rate": 3.953488372093024e-06,
+      "loss": 1.4646,
+      "step": 18
+    },
+    {
+      "epoch": 0.1329252295583734,
+      "grad_norm": 1.8995134830474854,
+      "learning_rate": 4.186046511627907e-06,
+      "loss": 1.4568,
+      "step": 19
+    },
+    {
+      "epoch": 0.139921294271972,
+      "grad_norm": 1.8199081420898438,
+      "learning_rate": 4.418604651162791e-06,
+      "loss": 1.4273,
+      "step": 20
+    },
+    {
+      "epoch": 0.14691735898557062,
+      "grad_norm": 1.699924111366272,
+      "learning_rate": 4.651162790697675e-06,
+      "loss": 1.436,
+      "step": 21
+    },
+    {
+      "epoch": 0.15391342369916922,
+      "grad_norm": 1.4117141962051392,
+      "learning_rate": 4.883720930232559e-06,
+      "loss": 1.3895,
+      "step": 22
+    },
+    {
+      "epoch": 0.1609094884127678,
+      "grad_norm": 1.1737254858016968,
+      "learning_rate": 5.116279069767442e-06,
+      "loss": 1.4017,
+      "step": 23
+    },
+    {
+      "epoch": 0.16790555312636643,
+      "grad_norm": 0.8299681544303894,
+      "learning_rate": 5.348837209302326e-06,
+      "loss": 1.3541,
+      "step": 24
+    },
+    {
+      "epoch": 0.17490161783996502,
+      "grad_norm": 0.9315920472145081,
+      "learning_rate": 5.58139534883721e-06,
+      "loss": 1.3462,
+      "step": 25
+    },
+    {
+      "epoch": 0.18189768255356362,
+      "grad_norm": 1.1129711866378784,
+      "learning_rate": 5.8139534883720935e-06,
+      "loss": 1.3078,
+      "step": 26
+    },
+    {
+      "epoch": 0.1888937472671622,
+      "grad_norm": 1.073608160018921,
+      "learning_rate": 6.046511627906977e-06,
+      "loss": 1.3173,
+      "step": 27
+    },
+    {
+      "epoch": 0.19588981198076083,
+      "grad_norm": 0.9064130783081055,
+      "learning_rate": 6.279069767441861e-06,
+      "loss": 1.2973,
+      "step": 28
+    },
+    {
+      "epoch": 0.20288587669435942,
+      "grad_norm": 0.7085795402526855,
+      "learning_rate": 6.511627906976745e-06,
+      "loss": 1.2819,
+      "step": 29
+    },
+    {
+      "epoch": 0.20988194140795802,
+      "grad_norm": 0.625628650188446,
+      "learning_rate": 6.744186046511628e-06,
+      "loss": 1.2715,
+      "step": 30
+    },
+    {
+      "epoch": 0.21687800612155664,
+      "grad_norm": 0.6054685115814209,
+      "learning_rate": 6.976744186046513e-06,
+      "loss": 1.2858,
+      "step": 31
+    },
+    {
+      "epoch": 0.22387407083515523,
+      "grad_norm": 0.6722832322120667,
+      "learning_rate": 7.209302325581395e-06,
+      "loss": 1.2616,
+      "step": 32
+    },
+    {
+      "epoch": 0.23087013554875382,
+      "grad_norm": 0.6375171542167664,
+      "learning_rate": 7.44186046511628e-06,
+      "loss": 1.2479,
+      "step": 33
+    },
+    {
+      "epoch": 0.23786620026235242,
+      "grad_norm": 0.5648869872093201,
+      "learning_rate": 7.674418604651164e-06,
+      "loss": 1.2181,
+      "step": 34
+    },
+    {
+      "epoch": 0.24486226497595104,
+      "grad_norm": 0.5544123649597168,
+      "learning_rate": 7.906976744186048e-06,
+      "loss": 1.2149,
+      "step": 35
+    },
+    {
+      "epoch": 0.25185832968954963,
+      "grad_norm": 0.5275465846061707,
+      "learning_rate": 8.139534883720931e-06,
+      "loss": 1.215,
+      "step": 36
+    },
+    {
+      "epoch": 0.2588543944031482,
+      "grad_norm": 0.5007346868515015,
+      "learning_rate": 8.372093023255815e-06,
+      "loss": 1.2235,
+      "step": 37
+    },
+    {
+      "epoch": 0.2658504591167468,
+      "grad_norm": 0.4550033509731293,
+      "learning_rate": 8.604651162790698e-06,
+      "loss": 1.2284,
+      "step": 38
+    },
+    {
+      "epoch": 0.2728465238303454,
+      "grad_norm": 0.4190613031387329,
+      "learning_rate": 8.837209302325582e-06,
+      "loss": 1.225,
+      "step": 39
+    },
+    {
+      "epoch": 0.279842588543944,
+      "grad_norm": 0.41906407475471497,
+      "learning_rate": 9.069767441860465e-06,
+      "loss": 1.1983,
+      "step": 40
+    },
+    {
+      "epoch": 0.28683865325754265,
+      "grad_norm": 0.42890453338623047,
+      "learning_rate": 9.30232558139535e-06,
+      "loss": 1.198,
+      "step": 41
+    },
+    {
+      "epoch": 0.29383471797114125,
+      "grad_norm": 0.4086310863494873,
+      "learning_rate": 9.534883720930234e-06,
+      "loss": 1.1938,
+      "step": 42
+    },
+    {
+      "epoch": 0.30083078268473984,
+      "grad_norm": 0.3552049696445465,
+      "learning_rate": 9.767441860465117e-06,
+      "loss": 1.184,
+      "step": 43
+    },
+    {
+      "epoch": 0.30782684739833843,
+      "grad_norm": 0.3367118835449219,
+      "learning_rate": 1e-05,
+      "loss": 1.2141,
+      "step": 44
+    },
+    {
+      "epoch": 0.314822912111937,
+      "grad_norm": 0.33877724409103394,
+      "learning_rate": 9.999834399079165e-06,
+      "loss": 1.1908,
+      "step": 45
+    },
+    {
+      "epoch": 0.3218189768255356,
+      "grad_norm": 0.33725035190582275,
+      "learning_rate": 9.99933760728612e-06,
+      "loss": 1.1937,
+      "step": 46
+    },
+    {
+      "epoch": 0.3288150415391342,
+      "grad_norm": 0.3173794746398926,
+      "learning_rate": 9.998509657528542e-06,
+      "loss": 1.1806,
+      "step": 47
+    },
+    {
+      "epoch": 0.33581110625273286,
+      "grad_norm": 0.29912763833999634,
+      "learning_rate": 9.997350604650123e-06,
+      "loss": 1.1903,
+      "step": 48
+    },
+    {
+      "epoch": 0.34280717096633145,
+      "grad_norm": 0.3210199773311615,
+      "learning_rate": 9.995860525426954e-06,
+      "loss": 1.1714,
+      "step": 49
+    },
+    {
+      "epoch": 0.34980323567993005,
+      "grad_norm": 0.28884193301200867,
+      "learning_rate": 9.994039518562433e-06,
+      "loss": 1.17,
+      "step": 50
+    },
+    {
+      "epoch": 0.35679930039352864,
+      "grad_norm": 0.25813987851142883,
+      "learning_rate": 9.991887704680723e-06,
+      "loss": 1.1642,
+      "step": 51
+    },
+    {
+      "epoch": 0.36379536510712723,
+      "grad_norm": 0.2741638422012329,
+      "learning_rate": 9.989405226318772e-06,
+      "loss": 1.1198,
+      "step": 52
+    },
+    {
+      "epoch": 0.3707914298207258,
+      "grad_norm": 0.3083779513835907,
+      "learning_rate": 9.986592247916859e-06,
+      "loss": 1.1353,
+      "step": 53
+    },
+    {
+      "epoch": 0.3777874945343244,
+      "grad_norm": 0.2932995855808258,
+      "learning_rate": 9.983448955807708e-06,
+      "loss": 1.211,
+      "step": 54
+    },
+    {
+      "epoch": 0.38478355924792307,
+      "grad_norm": 0.23885010182857513,
+      "learning_rate": 9.979975558204147e-06,
+      "loss": 1.1439,
+      "step": 55
+    },
+    {
+      "epoch": 0.39177962396152166,
+      "grad_norm": 0.2579386830329895,
+      "learning_rate": 9.976172285185315e-06,
+      "loss": 1.1625,
+      "step": 56
+    },
+    {
+      "epoch": 0.39877568867512025,
+      "grad_norm": 0.27125871181488037,
+      "learning_rate": 9.972039388681414e-06,
+      "loss": 1.1102,
+      "step": 57
+    },
+    {
+      "epoch": 0.40577175338871885,
+      "grad_norm": 0.2614425718784332,
+      "learning_rate": 9.967577142457031e-06,
+      "loss": 1.1594,
+      "step": 58
+    },
+    {
+      "epoch": 0.41276781810231744,
+      "grad_norm": 0.2357616126537323,
+      "learning_rate": 9.962785842093003e-06,
+      "loss": 1.1342,
+      "step": 59
+    },
+    {
+      "epoch": 0.41976388281591603,
+      "grad_norm": 0.22918762266635895,
+      "learning_rate": 9.95766580496683e-06,
+      "loss": 1.1322,
+      "step": 60
+    },
+    {
+      "epoch": 0.4267599475295146,
+      "grad_norm": 0.25597265362739563,
+      "learning_rate": 9.952217370231655e-06,
+      "loss": 1.1187,
+      "step": 61
+    },
+    {
+      "epoch": 0.4337560122431133,
+      "grad_norm": 0.2547328770160675,
+      "learning_rate": 9.9464408987938e-06,
+      "loss": 1.1426,
+      "step": 62
+    },
+    {
+      "epoch": 0.44075207695671187,
+      "grad_norm": 0.2541535794734955,
+      "learning_rate": 9.940336773288865e-06,
+      "loss": 1.1567,
+      "step": 63
+    },
+    {
+      "epoch": 0.44774814167031046,
+      "grad_norm": 0.23748283088207245,
+      "learning_rate": 9.933905398056371e-06,
+      "loss": 1.1432,
+      "step": 64
+    },
+    {
+      "epoch": 0.45474420638390906,
+      "grad_norm": 0.24227821826934814,
+      "learning_rate": 9.92714719911298e-06,
+      "loss": 1.114,
+      "step": 65
+    },
+    {
+      "epoch": 0.46174027109750765,
+      "grad_norm": 0.23363572359085083,
+      "learning_rate": 9.920062624124282e-06,
+      "loss": 1.1264,
+      "step": 66
+    },
+    {
+      "epoch": 0.46873633581110624,
+      "grad_norm": 0.2382754236459732,
+      "learning_rate": 9.912652142375132e-06,
+      "loss": 1.1231,
+      "step": 67
+    },
+    {
+      "epoch": 0.47573240052470483,
+      "grad_norm": 0.23080326616764069,
+      "learning_rate": 9.904916244738572e-06,
+      "loss": 1.1208,
+      "step": 68
+    },
+    {
+      "epoch": 0.48272846523830343,
+      "grad_norm": 0.23944209516048431,
+      "learning_rate": 9.896855443643307e-06,
+      "loss": 1.1334,
+      "step": 69
+    },
+    {
+      "epoch": 0.4897245299519021,
+      "grad_norm": 0.22721773386001587,
+      "learning_rate": 9.888470273039776e-06,
+      "loss": 1.1437,
+      "step": 70
+    },
+    {
+      "epoch": 0.49672059466550067,
+      "grad_norm": 0.22420594096183777,
+      "learning_rate": 9.879761288364767e-06,
+      "loss": 1.1297,
+      "step": 71
+    },
+    {
+      "epoch": 0.5037166593790993,
+      "grad_norm": 0.23493662476539612,
+      "learning_rate": 9.870729066504629e-06,
+      "loss": 1.1463,
+      "step": 72
+    },
+    {
+      "epoch": 0.5107127240926979,
+      "grad_norm": 0.23642633855342865,
+      "learning_rate": 9.861374205757068e-06,
+      "loss": 1.1529,
+      "step": 73
+    },
+    {
+      "epoch": 0.5177087888062964,
+      "grad_norm": 0.2463693767786026,
+      "learning_rate": 9.851697325791505e-06,
+      "loss": 1.1322,
+      "step": 74
+    },
+    {
+      "epoch": 0.524704853519895,
+      "grad_norm": 0.226633682847023,
+      "learning_rate": 9.841699067608034e-06,
+      "loss": 1.1109,
+      "step": 75
+    },
+    {
+      "epoch": 0.5317009182334936,
+      "grad_norm": 0.22586405277252197,
+      "learning_rate": 9.831380093494957e-06,
+      "loss": 1.1295,
+      "step": 76
+    },
+    {
+      "epoch": 0.5386969829470922,
+      "grad_norm": 0.24850787222385406,
+      "learning_rate": 9.820741086984925e-06,
+      "loss": 1.1173,
+      "step": 77
+    },
+    {
+      "epoch": 0.5456930476606908,
+      "grad_norm": 0.21549104154109955,
+      "learning_rate": 9.809782752809644e-06,
+      "loss": 1.1105,
+      "step": 78
+    },
+    {
+      "epoch": 0.5526891123742894,
+      "grad_norm": 0.2411831021308899,
+      "learning_rate": 9.798505816853207e-06,
+      "loss": 1.1275,
+      "step": 79
+    },
+    {
+      "epoch": 0.559685177087888,
+      "grad_norm": 0.22199593484401703,
+      "learning_rate": 9.786911026104007e-06,
+      "loss": 1.144,
+      "step": 80
+    },
+    {
+      "epoch": 0.5666812418014867,
+      "grad_norm": 0.23231951892375946,
+      "learning_rate": 9.77499914860525e-06,
+      "loss": 1.1094,
+      "step": 81
+    },
+    {
+      "epoch": 0.5736773065150853,
+      "grad_norm": 0.21762272715568542,
+      "learning_rate": 9.762770973404094e-06,
+      "loss": 1.1342,
+      "step": 82
+    },
+    {
+      "epoch": 0.5806733712286839,
+      "grad_norm": 0.24040056765079498,
+      "learning_rate": 9.750227310499365e-06,
+      "loss": 1.1249,
+      "step": 83
+    },
+    {
+      "epoch": 0.5876694359422825,
+      "grad_norm": 0.2038600593805313,
+      "learning_rate": 9.737368990787917e-06,
+      "loss": 1.1101,
+      "step": 84
+    },
+    {
+      "epoch": 0.5946655006558811,
+      "grad_norm": 0.21895648539066315,
+      "learning_rate": 9.72419686600958e-06,
+      "loss": 1.14,
+      "step": 85
+    },
+    {
+      "epoch": 0.6016615653694797,
+      "grad_norm": 0.2130373865365982,
+      "learning_rate": 9.710711808690754e-06,
+      "loss": 1.1365,
+      "step": 86
+    },
+    {
+      "epoch": 0.6086576300830783,
+      "grad_norm": 0.21359188854694366,
+      "learning_rate": 9.696914712086603e-06,
+      "loss": 1.1131,
+      "step": 87
+    },
+    {
+      "epoch": 0.6156536947966769,
+      "grad_norm": 0.20822754502296448,
+      "learning_rate": 9.682806490121886e-06,
+      "loss": 1.0983,
+      "step": 88
+    },
+    {
+      "epoch": 0.6226497595102755,
+      "grad_norm": 0.2118270844221115,
+      "learning_rate": 9.668388077330421e-06,
+      "loss": 1.1303,
+      "step": 89
+    },
+    {
+      "epoch": 0.629645824223874,
+      "grad_norm": 0.2127324342727661,
+      "learning_rate": 9.653660428793188e-06,
+      "loss": 1.123,
+      "step": 90
+    },
+    {
+      "epoch": 0.6366418889374726,
+      "grad_norm": 0.2167566865682602,
+      "learning_rate": 9.638624520075047e-06,
+      "loss": 1.0954,
+      "step": 91
+    },
+    {
+      "epoch": 0.6436379536510712,
+      "grad_norm": 0.21658548712730408,
+      "learning_rate": 9.623281347160129e-06,
+      "loss": 1.1189,
+      "step": 92
+    },
+    {
+      "epoch": 0.6506340183646698,
+      "grad_norm": 0.2170240879058838,
+      "learning_rate": 9.60763192638586e-06,
+      "loss": 1.1422,
+      "step": 93
+    },
+    {
+      "epoch": 0.6576300830782684,
+      "grad_norm": 0.2205752283334732,
+      "learning_rate": 9.591677294375637e-06,
+      "loss": 1.1389,
+      "step": 94
+    },
+    {
+      "epoch": 0.6646261477918671,
+      "grad_norm": 0.22668494284152985,
+      "learning_rate": 9.57541850797016e-06,
+      "loss": 1.1174,
+      "step": 95
+    },
+    {
+      "epoch": 0.6716222125054657,
+      "grad_norm": 0.2228441834449768,
+      "learning_rate": 9.558856644157432e-06,
+      "loss": 1.0944,
+      "step": 96
+    },
+    {
+      "epoch": 0.6786182772190643,
+      "grad_norm": 0.23455341160297394,
+      "learning_rate": 9.54199280000141e-06,
+      "loss": 1.1025,
+      "step": 97
+    },
+    {
+      "epoch": 0.6856143419326629,
+      "grad_norm": 0.24054673314094543,
+      "learning_rate": 9.52482809256934e-06,
+      "loss": 1.081,
+      "step": 98
+    },
+    {
+      "epoch": 0.6926104066462615,
+      "grad_norm": 0.22918441891670227,
+      "learning_rate": 9.507363658857768e-06,
+      "loss": 1.0966,
+      "step": 99
+    },
+    {
+      "epoch": 0.6996064713598601,
+      "grad_norm": 0.21981216967105865,
+      "learning_rate": 9.489600655717217e-06,
+      "loss": 1.1064,
+      "step": 100
+    },
+    {
+      "epoch": 0.7066025360734587,
+      "grad_norm": 0.2228814661502838,
+      "learning_rate": 9.471540259775554e-06,
+      "loss": 1.1163,
+      "step": 101
+    },
+    {
+      "epoch": 0.7135986007870573,
+      "grad_norm": 0.2345104068517685,
+      "learning_rate": 9.453183667360062e-06,
+      "loss": 1.1049,
+      "step": 102
+    },
+    {
+      "epoch": 0.7205946655006559,
+      "grad_norm": 0.22801828384399414,
+      "learning_rate": 9.43453209441818e-06,
+      "loss": 1.1351,
+      "step": 103
+    },
+    {
+      "epoch": 0.7275907302142545,
+      "grad_norm": 0.2263229787349701,
+      "learning_rate": 9.415586776436973e-06,
+      "loss": 1.1206,
+      "step": 104
+    },
+    {
+      "epoch": 0.7345867949278531,
+      "grad_norm": 0.2334379404783249,
+      "learning_rate": 9.396348968361282e-06,
+      "loss": 1.109,
+      "step": 105
+    },
+    {
+      "epoch": 0.7415828596414517,
+      "grad_norm": 0.2365368753671646,
+      "learning_rate": 9.376819944510598e-06,
+      "loss": 1.1303,
+      "step": 106
+    },
+    {
+      "epoch": 0.7485789243550502,
+      "grad_norm": 0.21456782519817352,
+      "learning_rate": 9.357000998494656e-06,
+      "loss": 1.134,
+      "step": 107
+    },
+    {
+      "epoch": 0.7555749890686488,
+      "grad_norm": 0.23137013614177704,
+      "learning_rate": 9.336893443127739e-06,
+      "loss": 1.1111,
+      "step": 108
+    },
+    {
+      "epoch": 0.7625710537822474,
+      "grad_norm": 0.24741332232952118,
+      "learning_rate": 9.31649861034172e-06,
+      "loss": 1.1274,
+      "step": 109
+    },
+    {
+      "epoch": 0.7695671184958461,
+      "grad_norm": 0.2252303510904312,
+      "learning_rate": 9.295817851097836e-06,
+      "loss": 1.1148,
+      "step": 110
+    },
+    {
+      "epoch": 0.7765631832094447,
+      "grad_norm": 0.2318602055311203,
+      "learning_rate": 9.274852535297198e-06,
+      "loss": 1.0909,
+      "step": 111
+    },
+    {
+      "epoch": 0.7835592479230433,
+      "grad_norm": 0.2182338833808899,
+      "learning_rate": 9.253604051690047e-06,
+      "loss": 1.1083,
+      "step": 112
+    },
+    {
+      "epoch": 0.7905553126366419,
+      "grad_norm": 0.21458062529563904,
+      "learning_rate": 9.232073807783758e-06,
+      "loss": 1.0834,
+      "step": 113
+    },
+    {
+      "epoch": 0.7975513773502405,
+      "grad_norm": 0.23873740434646606,
+      "learning_rate": 9.210263229749626e-06,
+      "loss": 1.1112,
+      "step": 114
+    },
+    {
+      "epoch": 0.8045474420638391,
+      "grad_norm": 0.21488192677497864,
+      "learning_rate": 9.188173762328367e-06,
+      "loss": 1.1006,
+      "step": 115
+    },
+    {
+      "epoch": 0.8115435067774377,
+      "grad_norm": 0.21982012689113617,
+      "learning_rate": 9.165806868734444e-06,
+      "loss": 1.0976,
+      "step": 116
+    },
+    {
+      "epoch": 0.8185395714910363,
+      "grad_norm": 0.21686458587646484,
+      "learning_rate": 9.143164030559122e-06,
+      "loss": 1.107,
+      "step": 117
+    },
+    {
+      "epoch": 0.8255356362046349,
+      "grad_norm": 0.263600617647171,
+      "learning_rate": 9.120246747672347e-06,
+      "loss": 1.1212,
+      "step": 118
+    },
+    {
+      "epoch": 0.8325317009182335,
+      "grad_norm": 0.28033727407455444,
+      "learning_rate": 9.097056538123376e-06,
+      "loss": 1.1081,
+      "step": 119
+    },
+    {
+      "epoch": 0.8395277656318321,
+      "grad_norm": 0.24289295077323914,
+      "learning_rate": 9.073594938040231e-06,
+      "loss": 1.0847,
+      "step": 120
+    },
+    {
+      "epoch": 0.8465238303454307,
+      "grad_norm": 0.22813363373279572,
+      "learning_rate": 9.049863501527947e-06,
+      "loss": 1.0969,
+      "step": 121
+    },
+    {
+      "epoch": 0.8535198950590293,
+      "grad_norm": 0.2539902329444885,
+      "learning_rate": 9.025863800565614e-06,
+      "loss": 1.0889,
+      "step": 122
+    },
+    {
+      "epoch": 0.8605159597726278,
+      "grad_norm": 0.2315206080675125,
+      "learning_rate": 9.001597424902266e-06,
+      "loss": 1.097,
+      "step": 123
+    },
+    {
+      "epoch": 0.8675120244862266,
+      "grad_norm": 0.24084997177124023,
+      "learning_rate": 8.977065981951567e-06,
+      "loss": 1.1,
+      "step": 124
+    },
+    {
+      "epoch": 0.8745080891998251,
+      "grad_norm": 0.2634861469268799,
+      "learning_rate": 8.952271096685333e-06,
+      "loss": 1.0959,
+      "step": 125
+    },
+    {
+      "epoch": 0.8815041539134237,
+      "grad_norm": 0.25653111934661865,
+      "learning_rate": 8.927214411525895e-06,
+      "loss": 1.0794,
+      "step": 126
+    },
+    {
+      "epoch": 0.8885002186270223,
+      "grad_norm": 0.25337570905685425,
+      "learning_rate": 8.901897586237309e-06,
+      "loss": 1.1036,
+      "step": 127
+    },
+    {
+      "epoch": 0.8954962833406209,
+      "grad_norm": 0.26657527685165405,
+      "learning_rate": 8.876322297815406e-06,
+      "loss": 1.0841,
+      "step": 128
+    },
+    {
+      "epoch": 0.9024923480542195,
+      "grad_norm": 0.2519988715648651,
+      "learning_rate": 8.85049024037671e-06,
+      "loss": 1.0646,
+      "step": 129
+    },
+    {
+      "epoch": 0.9094884127678181,
+      "grad_norm": 0.24986772239208221,
+      "learning_rate": 8.824403125046225e-06,
+      "loss": 1.0926,
+      "step": 130
+    },
+    {
+      "epoch": 0.9164844774814167,
+      "grad_norm": 0.24577908217906952,
+      "learning_rate": 8.798062679844077e-06,
+      "loss": 1.1129,
+      "step": 131
+    },
+    {
+      "epoch": 0.9234805421950153,
+      "grad_norm": 0.23117944598197937,
+      "learning_rate": 8.771470649571056e-06,
+      "loss": 1.0917,
+      "step": 132
+    },
+    {
+      "epoch": 0.9304766069086139,
+      "grad_norm": 0.2600792348384857,
+      "learning_rate": 8.744628795693046e-06,
+      "loss": 1.088,
+      "step": 133
+    },
+    {
+      "epoch": 0.9374726716222125,
+      "grad_norm": 0.23922646045684814,
+      "learning_rate": 8.717538896224333e-06,
+      "loss": 1.0707,
+      "step": 134
+    },
+    {
+      "epoch": 0.9444687363358111,
+      "grad_norm": 0.2643781006336212,
+      "learning_rate": 8.690202745609834e-06,
+      "loss": 1.0909,
+      "step": 135
+    },
+    {
+      "epoch": 0.9514648010494097,
+      "grad_norm": 0.23887589573860168,
+      "learning_rate": 8.662622154606238e-06,
+      "loss": 1.1139,
+      "step": 136
+    },
+    {
+      "epoch": 0.9584608657630083,
+      "grad_norm": 0.2613793909549713,
+      "learning_rate": 8.634798950162048e-06,
+      "loss": 1.124,
+      "step": 137
+    },
+    {
+      "epoch": 0.9654569304766069,
+      "grad_norm": 0.24978399276733398,
+      "learning_rate": 8.606734975296578e-06,
+      "loss": 1.0895,
+      "step": 138
+    },
+    {
+      "epoch": 0.9724529951902056,
+      "grad_norm": 0.2559661567211151,
+      "learning_rate": 8.57843208897786e-06,
+      "loss": 1.0957,
+      "step": 139
+    },
+    {
+      "epoch": 0.9794490599038042,
+      "grad_norm": 0.2543698251247406,
+      "learning_rate": 8.549892165999505e-06,
+      "loss": 1.0915,
+      "step": 140
+    },
+    {
+      "epoch": 0.9864451246174027,
+      "grad_norm": 0.24577634036540985,
+      "learning_rate": 8.521117096856529e-06,
+      "loss": 1.062,
+      "step": 141
+    },
+    {
+      "epoch": 0.9934411893310013,
+      "grad_norm": 0.2525068521499634,
+      "learning_rate": 8.492108787620106e-06,
+      "loss": 1.0943,
+      "step": 142
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2525068521499634,
+      "learning_rate": 8.462869159811326e-06,
+      "loss": 1.1121,
+      "step": 143
+    },
+    {
+      "epoch": 1.0069960647135987,
+      "grad_norm": 0.2555246353149414,
+      "learning_rate": 8.433400150273907e-06,
+      "loss": 1.0907,
+      "step": 144
+    },
+    {
+      "epoch": 1.0139921294271972,
+      "grad_norm": 0.24802914261817932,
+      "learning_rate": 8.403703711045892e-06,
+      "loss": 1.0606,
+      "step": 145
+    },
+    {
+      "epoch": 1.020988194140796,
+      "grad_norm": 0.2563156187534332,
+      "learning_rate": 8.373781809230355e-06,
+      "loss": 1.077,
+      "step": 146
+    },
+    {
+      "epoch": 1.0279842588543944,
+      "grad_norm": 0.2540357708930969,
+      "learning_rate": 8.343636426865096e-06,
+      "loss": 1.0391,
+      "step": 147
+    },
+    {
+      "epoch": 1.034980323567993,
+      "grad_norm": 0.2662995159626007,
+      "learning_rate": 8.313269560791343e-06,
+      "loss": 1.0696,
+      "step": 148
+    },
+    {
+      "epoch": 1.0419763882815916,
+      "grad_norm": 0.2547081410884857,
+      "learning_rate": 8.282683222521491e-06,
+      "loss": 1.0688,
+      "step": 149
+    },
+    {
+      "epoch": 1.0489724529951903,
+      "grad_norm": 0.2514967918395996,
+      "learning_rate": 8.251879438105854e-06,
+      "loss": 1.1046,
+      "step": 150
+    },
+    {
+      "epoch": 1.0559685177087887,
+      "grad_norm": 0.27139806747436523,
+      "learning_rate": 8.220860247998455e-06,
+      "loss": 1.0759,
+      "step": 151
+    },
+    {
+      "epoch": 1.0629645824223874,
+      "grad_norm": 0.24396289885044098,
+      "learning_rate": 8.189627706921876e-06,
+      "loss": 1.0824,
+      "step": 152
+    },
+    {
+      "epoch": 1.069960647135986,
+      "grad_norm": 0.24899303913116455,
+      "learning_rate": 8.15818388373114e-06,
+      "loss": 1.0773,
+      "step": 153
+    },
+    {
+      "epoch": 1.0769567118495846,
+      "grad_norm": 0.2431674599647522,
+      "learning_rate": 8.126530861276677e-06,
+      "loss": 1.0472,
+      "step": 154
+    },
+    {
+      "epoch": 1.0839527765631831,
+      "grad_norm": 0.25614264607429504,
+      "learning_rate": 8.094670736266352e-06,
+      "loss": 1.0477,
+      "step": 155
+    },
+    {
+      "epoch": 1.0909488412767818,
+      "grad_norm": 0.256788969039917,
+      "learning_rate": 8.062605619126585e-06,
+      "loss": 1.0631,
+      "step": 156
+    },
+    {
+      "epoch": 1.0979449059903805,
+      "grad_norm": 0.25251755118370056,
+      "learning_rate": 8.030337633862542e-06,
+      "loss": 1.0779,
+      "step": 157
+    },
+    {
+      "epoch": 1.104940970703979,
+      "grad_norm": 0.25813043117523193,
+      "learning_rate": 7.997868917917453e-06,
+      "loss": 1.0479,
+      "step": 158
+    },
+    {
+      "epoch": 1.1119370354175777,
+      "grad_norm": 0.2598208487033844,
+      "learning_rate": 7.96520162203102e-06,
+      "loss": 1.0432,
+      "step": 159
+    },
+    {
+      "epoch": 1.1189331001311762,
+      "grad_norm": 0.22656458616256714,
+      "learning_rate": 7.93233791009696e-06,
+      "loss": 1.0574,
+      "step": 160
+    },
+    {
+      "epoch": 1.125929164844775,
+      "grad_norm": 0.27121832966804504,
+      "learning_rate": 7.899279959019654e-06,
+      "loss": 1.0614,
+      "step": 161
+    },
+    {
+      "epoch": 1.1329252295583734,
+      "grad_norm": 0.24976760149002075,
+      "learning_rate": 7.866029958569956e-06,
+      "loss": 1.0609,
+      "step": 162
+    },
+    {
+      "epoch": 1.139921294271972,
+      "grad_norm": 0.26583290100097656,
+      "learning_rate": 7.832590111240145e-06,
+      "loss": 1.0751,
+      "step": 163
+    },
+    {
+      "epoch": 1.1469173589855706,
+      "grad_norm": 0.2444482296705246,
+      "learning_rate": 7.798962632098024e-06,
+      "loss": 1.0486,
+      "step": 164
+    },
+    {
+      "epoch": 1.1539134236991693,
+      "grad_norm": 0.23971612751483917,
+      "learning_rate": 7.765149748640198e-06,
+      "loss": 1.0725,
+      "step": 165
+    },
+    {
+      "epoch": 1.1609094884127678,
+      "grad_norm": 0.25408315658569336,
+      "learning_rate": 7.73115370064452e-06,
+      "loss": 1.0601,
+      "step": 166
+    },
+    {
+      "epoch": 1.1679055531263665,
+      "grad_norm": 0.258532851934433,
+      "learning_rate": 7.696976740021734e-06,
+      "loss": 1.0614,
+      "step": 167
+    },
+    {
+      "epoch": 1.174901617839965,
+      "grad_norm": 0.2614459693431854,
+      "learning_rate": 7.6626211306663e-06,
+      "loss": 1.0903,
+      "step": 168
+    },
+    {
+      "epoch": 1.1818976825535636,
+      "grad_norm": 0.2806360423564911,
+      "learning_rate": 7.628089148306434e-06,
+      "loss": 1.0728,
+      "step": 169
+    },
+    {
+      "epoch": 1.1888937472671621,
+      "grad_norm": 0.2813877761363983,
+      "learning_rate": 7.593383080353369e-06,
+      "loss": 1.0673,
+      "step": 170
+    },
+    {
+      "epoch": 1.1958898119807608,
+      "grad_norm": 0.2591645419597626,
+      "learning_rate": 7.558505225749827e-06,
+      "loss": 1.0572,
+      "step": 171
+    },
+    {
+      "epoch": 1.2028858766943595,
+      "grad_norm": 0.26725247502326965,
+      "learning_rate": 7.523457894817745e-06,
+      "loss": 1.0631,
+      "step": 172
+    },
+    {
+      "epoch": 1.209881941407958,
+      "grad_norm": 0.2482025921344757,
+      "learning_rate": 7.488243409105234e-06,
+      "loss": 1.0876,
+      "step": 173
+    },
+    {
+      "epoch": 1.2168780061215567,
+      "grad_norm": 0.25393399596214294,
+      "learning_rate": 7.452864101232798e-06,
+      "loss": 1.0499,
+      "step": 174
+    },
+    {
+      "epoch": 1.2238740708351552,
+      "grad_norm": 0.2386392503976822,
+      "learning_rate": 7.4173223147388215e-06,
+      "loss": 1.07,
+      "step": 175
+    },
+    {
+      "epoch": 1.230870135548754,
+      "grad_norm": 0.24232785403728485,
+      "learning_rate": 7.381620403924333e-06,
+      "loss": 1.0705,
+      "step": 176
+    },
+    {
+      "epoch": 1.2378662002623524,
+      "grad_norm": 0.25469738245010376,
+      "learning_rate": 7.3457607336970545e-06,
+      "loss": 1.0693,
+      "step": 177
+    },
+    {
+      "epoch": 1.244862264975951,
+      "grad_norm": 0.2506999373435974,
+      "learning_rate": 7.309745679414751e-06,
+      "loss": 1.0642,
+      "step": 178
+    },
+    {
+      "epoch": 1.2518583296895496,
+      "grad_norm": 0.24194584786891937,
+      "learning_rate": 7.273577626727884e-06,
+      "loss": 1.0586,
+      "step": 179
+    },
+    {
+      "epoch": 1.2588543944031483,
+      "grad_norm": 0.23366078734397888,
+      "learning_rate": 7.237258971421587e-06,
+      "loss": 1.094,
+      "step": 180
+    },
+    {
+      "epoch": 1.2658504591167468,
+      "grad_norm": 0.2570526599884033,
+      "learning_rate": 7.200792119256961e-06,
+      "loss": 1.0581,
+      "step": 181
+    },
+    {
+      "epoch": 1.2728465238303455,
+      "grad_norm": 0.22975337505340576,
+      "learning_rate": 7.164179485811728e-06,
+      "loss": 1.0732,
+      "step": 182
+    },
+    {
+      "epoch": 1.279842588543944,
+      "grad_norm": 0.23770399391651154,
+      "learning_rate": 7.127423496320212e-06,
+      "loss": 1.0757,
+      "step": 183
+    },
+    {
+      "epoch": 1.2868386532575427,
+      "grad_norm": 0.23923391103744507,
+      "learning_rate": 7.090526585512696e-06,
+      "loss": 1.0572,
+      "step": 184
+    },
+    {
+      "epoch": 1.2938347179711411,
+      "grad_norm": 0.23085491359233856,
+      "learning_rate": 7.053491197454142e-06,
+      "loss": 1.0492,
+      "step": 185
+    },
+    {
+      "epoch": 1.3008307826847398,
+      "grad_norm": 0.23270699381828308,
+      "learning_rate": 7.0163197853822975e-06,
+      "loss": 1.0816,
+      "step": 186
+    },
+    {
+      "epoch": 1.3078268473983385,
+      "grad_norm": 0.25381889939308167,
+      "learning_rate": 6.9790148115451894e-06,
+      "loss": 1.0785,
+      "step": 187
+    },
+    {
+      "epoch": 1.314822912111937,
+      "grad_norm": 0.2601195275783539,
+      "learning_rate": 6.941578747038024e-06,
+      "loss": 1.0795,
+      "step": 188
+    },
+    {
+      "epoch": 1.3218189768255355,
+      "grad_norm": 0.25882264971733093,
+      "learning_rate": 6.904014071639503e-06,
+      "loss": 1.0661,
+      "step": 189
+    },
+    {
+      "epoch": 1.3288150415391342,
+      "grad_norm": 0.26806139945983887,
+      "learning_rate": 6.866323273647564e-06,
+      "loss": 1.0567,
+      "step": 190
+    },
+    {
+      "epoch": 1.335811106252733,
+      "grad_norm": 0.23781196773052216,
+      "learning_rate": 6.828508849714546e-06,
+      "loss": 1.0519,
+      "step": 191
+    },
+    {
+      "epoch": 1.3428071709663314,
+      "grad_norm": 0.2429259866476059,
+      "learning_rate": 6.79057330468182e-06,
+      "loss": 1.062,
+      "step": 192
+    },
+    {
+      "epoch": 1.34980323567993,
+      "grad_norm": 0.25786203145980835,
+      "learning_rate": 6.752519151413862e-06,
+      "loss": 1.0565,
+      "step": 193
+    },
+    {
+      "epoch": 1.3567993003935286,
+      "grad_norm": 0.24636365473270416,
+      "learning_rate": 6.7143489106318e-06,
+      "loss": 1.0576,
+      "step": 194
+    },
+    {
+      "epoch": 1.3637953651071273,
+      "grad_norm": 0.249672532081604,
+      "learning_rate": 6.676065110746445e-06,
+      "loss": 1.0519,
+      "step": 195
+    },
+    {
+      "epoch": 1.3707914298207258,
+      "grad_norm": 0.23771335184574127,
+      "learning_rate": 6.6376702876908e-06,
+      "loss": 1.0544,
+      "step": 196
+    },
+    {
+      "epoch": 1.3777874945343245,
+      "grad_norm": 0.24842609465122223,
+      "learning_rate": 6.599166984752088e-06,
+      "loss": 1.085,
+      "step": 197
+    },
+    {
+      "epoch": 1.3847835592479232,
+      "grad_norm": 0.2690418064594269,
+      "learning_rate": 6.560557752403277e-06,
+      "loss": 1.0821,
+      "step": 198
+    },
+    {
+      "epoch": 1.3917796239615217,
+      "grad_norm": 0.25750598311424255,
+      "learning_rate": 6.52184514813414e-06,
+      "loss": 1.0432,
+      "step": 199
+    },
+    {
+      "epoch": 1.3987756886751201,
+      "grad_norm": 0.25249239802360535,
+      "learning_rate": 6.483031736281843e-06,
+      "loss": 1.0347,
+      "step": 200
+    },
+    {
+      "epoch": 1.4057717533887188,
+      "grad_norm": 0.22841164469718933,
+      "learning_rate": 6.444120087861081e-06,
+      "loss": 1.0727,
+      "step": 201
+    },
+    {
+      "epoch": 1.4127678181023176,
+      "grad_norm": 0.2515389621257782,
+      "learning_rate": 6.405112780393781e-06,
+      "loss": 1.0637,
+      "step": 202
+    },
+    {
+      "epoch": 1.419763882815916,
+      "grad_norm": 0.26256147027015686,
+      "learning_rate": 6.366012397738355e-06,
+      "loss": 1.0614,
+      "step": 203
+    },
+    {
+      "epoch": 1.4267599475295145,
+      "grad_norm": 0.21680590510368347,
+      "learning_rate": 6.3268215299185545e-06,
+      "loss": 1.0625,
+      "step": 204
+    },
+    {
+      "epoch": 1.4337560122431132,
+      "grad_norm": 0.25839176774024963,
+      "learning_rate": 6.2875427729518966e-06,
+      "loss": 1.0564,
+      "step": 205
+    },
+    {
+      "epoch": 1.440752076956712,
+      "grad_norm": 0.2728981077671051,
+      "learning_rate": 6.2481787286777116e-06,
+      "loss": 1.0603,
+      "step": 206
+    },
+    {
+      "epoch": 1.4477481416703104,
+      "grad_norm": 0.24710682034492493,
+      "learning_rate": 6.208732004584792e-06,
+      "loss": 1.0543,
+      "step": 207
+    },
+    {
+      "epoch": 1.454744206383909,
+      "grad_norm": 0.2378065139055252,
+      "learning_rate": 6.169205213638671e-06,
+      "loss": 1.0738,
+      "step": 208
+    },
+    {
+      "epoch": 1.4617402710975076,
+      "grad_norm": 0.2657370865345001,
+      "learning_rate": 6.129600974108538e-06,
+      "loss": 1.032,
+      "step": 209
+    },
+    {
+      "epoch": 1.4687363358111063,
+      "grad_norm": 0.2566014528274536,
+      "learning_rate": 6.089921909393812e-06,
+      "loss": 1.0558,
+      "step": 210
+    },
+    {
+      "epoch": 1.4757324005247048,
+      "grad_norm": 0.22705771028995514,
+      "learning_rate": 6.050170647850351e-06,
+      "loss": 1.0802,
+      "step": 211
+    },
+    {
+      "epoch": 1.4827284652383035,
+      "grad_norm": 0.25922277569770813,
+      "learning_rate": 6.01034982261636e-06,
+      "loss": 1.0505,
+      "step": 212
+    },
+    {
+      "epoch": 1.4897245299519022,
+      "grad_norm": 0.2328343391418457,
+      "learning_rate": 5.970462071437974e-06,
+      "loss": 1.0494,
+      "step": 213
+    },
+    {
+      "epoch": 1.4967205946655007,
+      "grad_norm": 0.24370628595352173,
+      "learning_rate": 5.93051003649452e-06,
+      "loss": 1.0714,
+      "step": 214
+    },
+    {
+      "epoch": 1.5037166593790992,
+      "grad_norm": 0.22944258153438568,
+      "learning_rate": 5.890496364223509e-06,
+      "loss": 1.0563,
+      "step": 215
+    },
+    {
+      "epoch": 1.5107127240926979,
+      "grad_norm": 0.2519015669822693,
+      "learning_rate": 5.850423705145334e-06,
+      "loss": 1.061,
+      "step": 216
+    },
+    {
+      "epoch": 1.5177087888062966,
+      "grad_norm": 0.24373194575309753,
+      "learning_rate": 5.810294713687687e-06,
+      "loss": 1.0485,
+      "step": 217
+    },
+    {
+      "epoch": 1.524704853519895,
+      "grad_norm": 0.25564828515052795,
+      "learning_rate": 5.770112048009747e-06,
+      "loss": 1.0205,
+      "step": 218
+    },
+    {
+      "epoch": 1.5317009182334935,
+      "grad_norm": 0.23328275978565216,
+      "learning_rate": 5.729878369826087e-06,
+      "loss": 1.0268,
+      "step": 219
+    },
+    {
+      "epoch": 1.5386969829470922,
+      "grad_norm": 0.23757322132587433,
+      "learning_rate": 5.68959634423037e-06,
+      "loss": 1.0677,
+      "step": 220
+    },
+    {
+      "epoch": 1.545693047660691,
+      "grad_norm": 0.2618321180343628,
+      "learning_rate": 5.64926863951881e-06,
+      "loss": 1.0499,
+      "step": 221
+    },
+    {
+      "epoch": 1.5526891123742894,
+      "grad_norm": 0.24455450475215912,
+      "learning_rate": 5.60889792701342e-06,
+      "loss": 1.0721,
+      "step": 222
+    },
+    {
+      "epoch": 1.559685177087888,
+      "grad_norm": 0.23317770659923553,
+      "learning_rate": 5.568486880885068e-06,
+      "loss": 1.0684,
+      "step": 223
+    },
+    {
+      "epoch": 1.5666812418014868,
+      "grad_norm": 0.2898538410663605,
+      "learning_rate": 5.52803817797633e-06,
+      "loss": 1.0489,
+      "step": 224
+    },
+    {
+      "epoch": 1.5736773065150853,
+      "grad_norm": 0.25492820143699646,
+      "learning_rate": 5.487554497624189e-06,
+      "loss": 1.0586,
+      "step": 225
+    },
+    {
+      "epoch": 1.5806733712286838,
+      "grad_norm": 0.26318982243537903,
+      "learning_rate": 5.447038521482542e-06,
+      "loss": 1.0661,
+      "step": 226
+    },
+    {
+      "epoch": 1.5876694359422825,
+      "grad_norm": 0.22720639407634735,
+      "learning_rate": 5.406492933344572e-06,
+      "loss": 1.0577,
+      "step": 227
+    },
+    {
+      "epoch": 1.5946655006558812,
+      "grad_norm": 0.24046605825424194,
+      "learning_rate": 5.365920418964973e-06,
+      "loss": 1.0828,
+      "step": 228
+    },
+    {
+      "epoch": 1.6016615653694797,
+      "grad_norm": 0.24605053663253784,
+      "learning_rate": 5.325323665882039e-06,
+      "loss": 1.0481,
+      "step": 229
+    },
+    {
+      "epoch": 1.6086576300830782,
+      "grad_norm": 0.23823630809783936,
+      "learning_rate": 5.284705363239651e-06,
+      "loss": 1.0625,
+      "step": 230
+    },
+    {
+      "epoch": 1.6156536947966769,
+      "grad_norm": 0.2552984058856964,
+      "learning_rate": 5.244068201609132e-06,
+      "loss": 1.0191,
+      "step": 231
+    },
+    {
+      "epoch": 1.6226497595102756,
+      "grad_norm": 0.22282664477825165,
+      "learning_rate": 5.203414872811042e-06,
+      "loss": 1.0397,
+      "step": 232
+    },
+    {
+      "epoch": 1.629645824223874,
+      "grad_norm": 0.24304307997226715,
+      "learning_rate": 5.162748069736851e-06,
+      "loss": 1.0434,
+      "step": 233
+    },
+    {
+      "epoch": 1.6366418889374725,
+      "grad_norm": 0.2629837095737457,
+      "learning_rate": 5.1220704861705775e-06,
+      "loss": 1.0691,
+      "step": 234
+    },
+    {
+      "epoch": 1.6436379536510712,
+      "grad_norm": 0.24670404195785522,
+      "learning_rate": 5.0813848166103365e-06,
+      "loss": 1.0791,
+      "step": 235
+    },
+    {
+      "epoch": 1.65063401836467,
+      "grad_norm": 0.2600962817668915,
+      "learning_rate": 5.040693756089865e-06,
+      "loss": 1.0499,
+      "step": 236
+    },
+    {
+      "epoch": 1.6576300830782684,
+      "grad_norm": 0.24187523126602173,
+      "learning_rate": 5e-06,
+      "loss": 1.0474,
+      "step": 237
+    },
+    {
+      "epoch": 1.6646261477918671,
+      "grad_norm": 0.22072897851467133,
+      "learning_rate": 4.959306243910137e-06,
+      "loss": 1.067,
+      "step": 238
+    },
+    {
+      "epoch": 1.6716222125054658,
+      "grad_norm": 0.2424023151397705,
+      "learning_rate": 4.918615183389666e-06,
+      "loss": 1.0621,
+      "step": 239
+    },
+    {
+      "epoch": 1.6786182772190643,
+      "grad_norm": 0.23267744481563568,
+      "learning_rate": 4.877929513829424e-06,
+      "loss": 1.0256,
+      "step": 240
+    },
+    {
+      "epoch": 1.6856143419326628,
+      "grad_norm": 0.21274727582931519,
+      "learning_rate": 4.837251930263149e-06,
+      "loss": 1.0725,
+      "step": 241
+    },
+    {
+      "epoch": 1.6926104066462615,
+      "grad_norm": 0.24191388487815857,
+      "learning_rate": 4.796585127188958e-06,
+      "loss": 1.0664,
+      "step": 242
+    },
+    {
+      "epoch": 1.6996064713598602,
+      "grad_norm": 0.2611248195171356,
+      "learning_rate": 4.755931798390867e-06,
+      "loss": 1.0731,
+      "step": 243
+    },
+    {
+      "epoch": 1.7066025360734587,
+      "grad_norm": 0.21119238436222076,
+      "learning_rate": 4.715294636760352e-06,
+      "loss": 1.0413,
+      "step": 244
+    },
+    {
+      "epoch": 1.7135986007870572,
+      "grad_norm": 0.23526926338672638,
+      "learning_rate": 4.674676334117962e-06,
+      "loss": 1.0519,
+      "step": 245
+    },
+    {
+      "epoch": 1.7205946655006559,
+      "grad_norm": 0.22488483786582947,
+      "learning_rate": 4.634079581035029e-06,
+      "loss": 1.0657,
+      "step": 246
+    },
+    {
+      "epoch": 1.7275907302142546,
+      "grad_norm": 0.23433709144592285,
+      "learning_rate": 4.59350706665543e-06,
+      "loss": 1.0365,
+      "step": 247
+    },
+    {
+      "epoch": 1.734586794927853,
+      "grad_norm": 0.22495707869529724,
+      "learning_rate": 4.5529614785174606e-06,
+      "loss": 1.0858,
+      "step": 248
+    },
+    {
+      "epoch": 1.7415828596414515,
+      "grad_norm": 0.23225753009319305,
+      "learning_rate": 4.512445502375813e-06,
+      "loss": 1.0752,
+      "step": 249
+    },
+    {
+      "epoch": 1.7485789243550502,
+      "grad_norm": 0.22089412808418274,
+      "learning_rate": 4.4719618220236715e-06,
+      "loss": 1.0862,
+      "step": 250
+    },
+    {
+      "epoch": 1.755574989068649,
+      "grad_norm": 0.21389490365982056,
+      "learning_rate": 4.431513119114934e-06,
+      "loss": 1.0688,
+      "step": 251
+    },
+    {
+      "epoch": 1.7625710537822474,
+      "grad_norm": 0.22955602407455444,
+      "learning_rate": 4.391102072986581e-06,
+      "loss": 1.058,
+      "step": 252
+    },
+    {
+      "epoch": 1.7695671184958461,
+      "grad_norm": 0.21846045553684235,
+      "learning_rate": 4.350731360481191e-06,
+      "loss": 1.0376,
+      "step": 253
+    },
+    {
+      "epoch": 1.7765631832094448,
+      "grad_norm": 0.21093875169754028,
+      "learning_rate": 4.310403655769629e-06,
+      "loss": 1.068,
+      "step": 254
+    },
+    {
+      "epoch": 1.7835592479230433,
+      "grad_norm": 0.23426657915115356,
+      "learning_rate": 4.270121630173913e-06,
+      "loss": 1.0326,
+      "step": 255
+    },
+    {
+      "epoch": 1.7905553126366418,
+      "grad_norm": 0.21856963634490967,
+      "learning_rate": 4.229887951990255e-06,
+      "loss": 1.0689,
+      "step": 256
+    },
+    {
+      "epoch": 1.7975513773502405,
+      "grad_norm": 0.21545103192329407,
+      "learning_rate": 4.189705286312314e-06,
+      "loss": 1.049,
+      "step": 257
+    },
+    {
+      "epoch": 1.8045474420638392,
+      "grad_norm": 0.21497775614261627,
+      "learning_rate": 4.149576294854668e-06,
+      "loss": 1.043,
+      "step": 258
+    },
+    {
+      "epoch": 1.8115435067774377,
+      "grad_norm": 0.22141148149967194,
+      "learning_rate": 4.109503635776492e-06,
+      "loss": 1.0592,
+      "step": 259
+    },
+    {
+      "epoch": 1.8185395714910362,
+      "grad_norm": 0.23661255836486816,
+      "learning_rate": 4.069489963505482e-06,
+      "loss": 1.0577,
+      "step": 260
+    },
+    {
+      "epoch": 1.8255356362046349,
+      "grad_norm": 0.21644575893878937,
+      "learning_rate": 4.029537928562028e-06,
+      "loss": 1.0427,
+      "step": 261
+    },
+    {
+      "epoch": 1.8325317009182336,
+      "grad_norm": 0.20113667845726013,
+      "learning_rate": 3.989650177383641e-06,
+      "loss": 1.0513,
+      "step": 262
+    },
+    {
+      "epoch": 1.839527765631832,
+      "grad_norm": 0.21667400002479553,
+      "learning_rate": 3.949829352149651e-06,
+      "loss": 1.0459,
+      "step": 263
+    },
+    {
+      "epoch": 1.8465238303454306,
+      "grad_norm": 0.23230302333831787,
+      "learning_rate": 3.91007809060619e-06,
+      "loss": 1.0586,
+      "step": 264
+    },
+    {
+      "epoch": 1.8535198950590293,
+      "grad_norm": 0.2070595771074295,
+      "learning_rate": 3.870399025891461e-06,
+      "loss": 1.0663,
+      "step": 265
+    },
+    {
+      "epoch": 1.860515959772628,
+      "grad_norm": 0.21182109415531158,
+      "learning_rate": 3.83079478636133e-06,
+      "loss": 1.0385,
+      "step": 266
+    },
+    {
+      "epoch": 1.8675120244862264,
+      "grad_norm": 0.2090914398431778,
+      "learning_rate": 3.791267995415208e-06,
+      "loss": 1.0601,
+      "step": 267
+    },
+    {
+      "epoch": 1.8745080891998251,
+      "grad_norm": 0.2156212478876114,
+      "learning_rate": 3.7518212713222905e-06,
+      "loss": 1.0639,
+      "step": 268
+    },
+    {
+      "epoch": 1.8815041539134238,
+      "grad_norm": 0.22998787462711334,
+      "learning_rate": 3.7124572270481055e-06,
+      "loss": 1.0389,
+      "step": 269
+    },
+    {
+      "epoch": 1.8885002186270223,
+      "grad_norm": 0.2200993150472641,
+      "learning_rate": 3.6731784700814476e-06,
+      "loss": 1.06,
+      "step": 270
+    },
+    {
+      "epoch": 1.8954962833406208,
+      "grad_norm": 0.2213740348815918,
+      "learning_rate": 3.633987602261647e-06,
+      "loss": 1.0496,
+      "step": 271
+    },
+    {
+      "epoch": 1.9024923480542195,
+      "grad_norm": 0.22220519185066223,
+      "learning_rate": 3.594887219606221e-06,
+      "loss": 1.0589,
+      "step": 272
+    },
+    {
+      "epoch": 1.9094884127678182,
+      "grad_norm": 0.24564726650714874,
+      "learning_rate": 3.55587991213892e-06,
+      "loss": 1.0556,
+      "step": 273
+    },
+    {
+      "epoch": 1.9164844774814167,
+      "grad_norm": 0.22368529438972473,
+      "learning_rate": 3.516968263718159e-06,
+      "loss": 1.0468,
+      "step": 274
+    },
+    {
+      "epoch": 1.9234805421950152,
+      "grad_norm": 0.2472257763147354,
+      "learning_rate": 3.47815485186586e-06,
+      "loss": 1.0512,
+      "step": 275
+    },
+    {
+      "epoch": 1.930476606908614,
+      "grad_norm": 0.22477369010448456,
+      "learning_rate": 3.439442247596724e-06,
+      "loss": 1.0738,
+      "step": 276
+    },
+    {
+      "epoch": 1.9374726716222126,
+      "grad_norm": 0.2397991418838501,
+      "learning_rate": 3.400833015247913e-06,
+      "loss": 1.0506,
+      "step": 277
+    },
+    {
+      "epoch": 1.944468736335811,
+      "grad_norm": 0.22635191679000854,
+      "learning_rate": 3.3623297123092007e-06,
+      "loss": 1.0504,
+      "step": 278
+    },
+    {
+      "epoch": 1.9514648010494096,
+      "grad_norm": 0.20439866185188293,
+      "learning_rate": 3.3239348892535562e-06,
+      "loss": 1.0505,
+      "step": 279
+    },
+    {
+      "epoch": 1.9584608657630083,
+      "grad_norm": 0.21743066608905792,
+      "learning_rate": 3.285651089368202e-06,
+      "loss": 1.0396,
+      "step": 280
+    },
+    {
+      "epoch": 1.965456930476607,
+      "grad_norm": 0.22120308876037598,
+      "learning_rate": 3.24748084858614e-06,
+      "loss": 1.0359,
+      "step": 281
+    },
+    {
+      "epoch": 1.9724529951902054,
+      "grad_norm": 0.23442624509334564,
+      "learning_rate": 3.2094266953181817e-06,
+      "loss": 1.0415,
+      "step": 282
+    },
+    {
+      "epoch": 1.9794490599038042,
+      "grad_norm": 0.22380927205085754,
+      "learning_rate": 3.1714911502854564e-06,
+      "loss": 1.0627,
+      "step": 283
+    },
+    {
+      "epoch": 1.9864451246174029,
+      "grad_norm": 0.22232678532600403,
+      "learning_rate": 3.133676726352438e-06,
+      "loss": 1.0586,
+      "step": 284
+    },
+    {
+      "epoch": 1.9934411893310013,
+      "grad_norm": 0.21684490144252777,
+      "learning_rate": 3.0959859283604984e-06,
+      "loss": 1.0469,
+      "step": 285
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.22368235886096954,
+      "learning_rate": 3.0584212529619777e-06,
+      "loss": 1.0719,
+      "step": 286
+    },
+    {
+      "epoch": 2.0069960647135985,
+      "grad_norm": 0.24952030181884766,
+      "learning_rate": 3.020985188454812e-06,
+      "loss": 1.0254,
+      "step": 287
+    },
+    {
+      "epoch": 2.0139921294271974,
+      "grad_norm": 0.23081070184707642,
+      "learning_rate": 2.9836802146177034e-06,
+      "loss": 1.0191,
+      "step": 288
+    },
+    {
+      "epoch": 2.020988194140796,
+      "grad_norm": 0.20420107245445251,
+      "learning_rate": 2.946508802545859e-06,
+      "loss": 1.0127,
+      "step": 289
+    },
+    {
+      "epoch": 2.0279842588543944,
+      "grad_norm": 0.21790923178195953,
+      "learning_rate": 2.9094734144873037e-06,
+      "loss": 1.0309,
+      "step": 290
+    },
+    {
+      "epoch": 2.034980323567993,
+      "grad_norm": 0.21608051657676697,
+      "learning_rate": 2.872576503679789e-06,
+      "loss": 1.0327,
+      "step": 291
+    },
+    {
+      "epoch": 2.041976388281592,
+      "grad_norm": 0.2340073436498642,
+      "learning_rate": 2.8358205141882735e-06,
+      "loss": 1.0441,
+      "step": 292
+    },
+    {
+      "epoch": 2.0489724529951903,
+      "grad_norm": 0.239246666431427,
+      "learning_rate": 2.7992078807430423e-06,
+      "loss": 1.0302,
+      "step": 293
+    },
+    {
+      "epoch": 2.0559685177087887,
+      "grad_norm": 0.21766602993011475,
+      "learning_rate": 2.7627410285784164e-06,
+      "loss": 1.0225,
+      "step": 294
+    },
+    {
+      "epoch": 2.0629645824223872,
+      "grad_norm": 0.2321794480085373,
+      "learning_rate": 2.726422373272117e-06,
+      "loss": 1.0251,
+      "step": 295
+    },
+    {
+      "epoch": 2.069960647135986,
+      "grad_norm": 0.22717420756816864,
+      "learning_rate": 2.6902543205852496e-06,
+      "loss": 1.0551,
+      "step": 296
+    },
+    {
+      "epoch": 2.0769567118495846,
+      "grad_norm": 0.2310858517885208,
+      "learning_rate": 2.6542392663029463e-06,
+      "loss": 1.0327,
+      "step": 297
+    },
+    {
+      "epoch": 2.083952776563183,
+      "grad_norm": 0.2265992909669876,
+      "learning_rate": 2.618379596075668e-06,
+      "loss": 1.0355,
+      "step": 298
+    },
+    {
+      "epoch": 2.0909488412767816,
+      "grad_norm": 0.203124538064003,
+      "learning_rate": 2.582677685261179e-06,
+      "loss": 1.0255,
+      "step": 299
+    },
+    {
+      "epoch": 2.0979449059903805,
+      "grad_norm": 0.2333555668592453,
+      "learning_rate": 2.547135898767202e-06,
+      "loss": 1.0389,
+      "step": 300
+    },
+    {
+      "epoch": 2.104940970703979,
+      "grad_norm": 0.25730496644973755,
+      "learning_rate": 2.511756590894765e-06,
+      "loss": 1.0423,
+      "step": 301
+    },
+    {
+      "epoch": 2.1119370354175775,
+      "grad_norm": 0.23582589626312256,
+      "learning_rate": 2.476542105182254e-06,
+      "loss": 1.037,
+      "step": 302
+    },
+    {
+      "epoch": 2.1189331001311764,
+      "grad_norm": 0.20338290929794312,
+      "learning_rate": 2.4414947742501743e-06,
+      "loss": 1.0454,
+      "step": 303
+    },
+    {
+      "epoch": 2.125929164844775,
+      "grad_norm": 0.21949388086795807,
+      "learning_rate": 2.4066169196466326e-06,
+      "loss": 1.0374,
+      "step": 304
+    },
+    {
+      "epoch": 2.1329252295583734,
+      "grad_norm": 0.21819548308849335,
+      "learning_rate": 2.3719108516935686e-06,
+      "loss": 1.0365,
+      "step": 305
+    },
+    {
+      "epoch": 2.139921294271972,
+      "grad_norm": 0.2275557965040207,
+      "learning_rate": 2.3373788693337024e-06,
+      "loss": 0.9914,
+      "step": 306
+    },
+    {
+      "epoch": 2.146917358985571,
+      "grad_norm": 0.20474126935005188,
+      "learning_rate": 2.303023259978267e-06,
+      "loss": 1.0061,
+      "step": 307
+    },
+    {
+      "epoch": 2.1539134236991693,
+      "grad_norm": 0.23000217974185944,
+      "learning_rate": 2.268846299355481e-06,
+      "loss": 1.0365,
+      "step": 308
+    },
+    {
+      "epoch": 2.1609094884127678,
+      "grad_norm": 0.20540106296539307,
+      "learning_rate": 2.2348502513598035e-06,
+      "loss": 1.019,
+      "step": 309
+    },
+    {
+      "epoch": 2.1679055531263662,
+      "grad_norm": 0.1969561129808426,
+      "learning_rate": 2.2010373679019773e-06,
+      "loss": 1.038,
+      "step": 310
+    },
+    {
+      "epoch": 2.174901617839965,
+      "grad_norm": 0.20978093147277832,
+      "learning_rate": 2.167409888759856e-06,
+      "loss": 1.0452,
+      "step": 311
+    },
+    {
+      "epoch": 2.1818976825535636,
+      "grad_norm": 0.2135351151227951,
+      "learning_rate": 2.133970041430044e-06,
+      "loss": 1.042,
+      "step": 312
+    },
+    {
+      "epoch": 2.188893747267162,
+      "grad_norm": 0.2012661248445511,
+      "learning_rate": 2.1007200409803465e-06,
+      "loss": 1.0197,
+      "step": 313
+    },
+    {
+      "epoch": 2.195889811980761,
+      "grad_norm": 0.20381034910678864,
+      "learning_rate": 2.0676620899030393e-06,
+      "loss": 1.0309,
+      "step": 314
+    },
+    {
+      "epoch": 2.2028858766943595,
+      "grad_norm": 0.21021777391433716,
+      "learning_rate": 2.03479837796898e-06,
+      "loss": 1.0455,
+      "step": 315
+    },
+    {
+      "epoch": 2.209881941407958,
+      "grad_norm": 0.2063123732805252,
+      "learning_rate": 2.002131082082549e-06,
+      "loss": 1.0391,
+      "step": 316
+    },
+    {
+      "epoch": 2.2168780061215565,
+      "grad_norm": 0.2144179344177246,
+      "learning_rate": 1.969662366137462e-06,
+      "loss": 1.0405,
+      "step": 317
+    },
+    {
+      "epoch": 2.2238740708351554,
+      "grad_norm": 0.20752228796482086,
+      "learning_rate": 1.937394380873418e-06,
+      "loss": 1.0358,
+      "step": 318
+    },
+    {
+      "epoch": 2.230870135548754,
+      "grad_norm": 0.19838763773441315,
+      "learning_rate": 1.905329263733649e-06,
+      "loss": 1.0507,
+      "step": 319
+    },
+    {
+      "epoch": 2.2378662002623524,
+      "grad_norm": 0.20437507331371307,
+      "learning_rate": 1.873469138723325e-06,
+      "loss": 1.0419,
+      "step": 320
+    },
+    {
+      "epoch": 2.244862264975951,
+      "grad_norm": 0.22749823331832886,
+      "learning_rate": 1.8418161162688613e-06,
+      "loss": 1.0287,
+      "step": 321
+    },
+    {
+      "epoch": 2.25185832968955,
+      "grad_norm": 0.21343137323856354,
+      "learning_rate": 1.8103722930781249e-06,
+      "loss": 1.0369,
+      "step": 322
+    },
+    {
+      "epoch": 2.2588543944031483,
+      "grad_norm": 0.22807368636131287,
+      "learning_rate": 1.7791397520015452e-06,
+      "loss": 1.017,
+      "step": 323
+    },
+    {
+      "epoch": 2.2658504591167468,
+      "grad_norm": 0.21017831563949585,
+      "learning_rate": 1.7481205618941472e-06,
+      "loss": 1.0313,
+      "step": 324
+    },
+    {
+      "epoch": 2.2728465238303452,
+      "grad_norm": 0.20900066196918488,
+      "learning_rate": 1.7173167774785093e-06,
+      "loss": 1.0436,
+      "step": 325
+    },
+    {
+      "epoch": 2.279842588543944,
+      "grad_norm": 0.21329908072948456,
+      "learning_rate": 1.6867304392086575e-06,
+      "loss": 1.0463,
+      "step": 326
+    },
+    {
+      "epoch": 2.2868386532575427,
+      "grad_norm": 0.1967432200908661,
+      "learning_rate": 1.656363573134906e-06,
+      "loss": 1.0489,
+      "step": 327
+    },
+    {
+      "epoch": 2.293834717971141,
+      "grad_norm": 0.18167762458324432,
+      "learning_rate": 1.6262181907696456e-06,
+      "loss": 1.0615,
+      "step": 328
+    },
+    {
+      "epoch": 2.3008307826847396,
+      "grad_norm": 0.19959093630313873,
+      "learning_rate": 1.5962962889541106e-06,
+      "loss": 1.0622,
+      "step": 329
+    },
+    {
+      "epoch": 2.3078268473983385,
+      "grad_norm": 0.21402791142463684,
+      "learning_rate": 1.5665998497260959e-06,
+      "loss": 1.0358,
+      "step": 330
+    },
+    {
+      "epoch": 2.314822912111937,
+      "grad_norm": 0.20190435647964478,
+      "learning_rate": 1.5371308401886759e-06,
+      "loss": 1.0502,
+      "step": 331
+    },
+    {
+      "epoch": 2.3218189768255355,
+      "grad_norm": 0.20728997886180878,
+      "learning_rate": 1.507891212379896e-06,
+      "loss": 1.0417,
+      "step": 332
+    },
+    {
+      "epoch": 2.3288150415391344,
+      "grad_norm": 0.20769530534744263,
+      "learning_rate": 1.4788829031434733e-06,
+      "loss": 1.0185,
+      "step": 333
+    },
+    {
+      "epoch": 2.335811106252733,
+      "grad_norm": 0.2038041651248932,
+      "learning_rate": 1.4501078340004954e-06,
+      "loss": 1.0182,
+      "step": 334
+    },
+    {
+      "epoch": 2.3428071709663314,
+      "grad_norm": 0.2017662227153778,
+      "learning_rate": 1.4215679110221415e-06,
+      "loss": 1.039,
+      "step": 335
+    },
+    {
+      "epoch": 2.34980323567993,
+      "grad_norm": 0.20630167424678802,
+      "learning_rate": 1.393265024703422e-06,
+      "loss": 1.0356,
+      "step": 336
+    },
+    {
+      "epoch": 2.356799300393529,
+      "grad_norm": 0.2051134705543518,
+      "learning_rate": 1.365201049837952e-06,
+      "loss": 1.0104,
+      "step": 337
+    },
+    {
+      "epoch": 2.3637953651071273,
+      "grad_norm": 0.2016696333885193,
+      "learning_rate": 1.337377845393763e-06,
+      "loss": 1.0409,
+      "step": 338
+    },
+    {
+      "epoch": 2.3707914298207258,
+      "grad_norm": 0.20232132077217102,
+      "learning_rate": 1.3097972543901672e-06,
+      "loss": 1.0453,
+      "step": 339
+    },
+    {
+      "epoch": 2.3777874945343243,
+      "grad_norm": 0.19618479907512665,
+      "learning_rate": 1.2824611037756686e-06,
+      "loss": 1.0414,
+      "step": 340
+    },
+    {
+      "epoch": 2.384783559247923,
+      "grad_norm": 0.19780609011650085,
+      "learning_rate": 1.255371204306956e-06,
+      "loss": 1.0428,
+      "step": 341
+    },
+    {
+      "epoch": 2.3917796239615217,
+      "grad_norm": 0.2076359987258911,
+      "learning_rate": 1.2285293504289448e-06,
+      "loss": 1.0204,
+      "step": 342
+    },
+    {
+      "epoch": 2.39877568867512,
+      "grad_norm": 0.19863395392894745,
+      "learning_rate": 1.2019373201559247e-06,
+      "loss": 1.018,
+      "step": 343
+    },
+    {
+      "epoch": 2.405771753388719,
+      "grad_norm": 0.1929175853729248,
+      "learning_rate": 1.1755968749537755e-06,
+      "loss": 1.0251,
+      "step": 344
+    },
+    {
+      "epoch": 2.4127678181023176,
+      "grad_norm": 0.1984327733516693,
+      "learning_rate": 1.1495097596232901e-06,
+      "loss": 1.0428,
+      "step": 345
+    },
+    {
+      "epoch": 2.419763882815916,
+      "grad_norm": 0.18438038229942322,
+      "learning_rate": 1.1236777021845957e-06,
+      "loss": 1.0368,
+      "step": 346
+    },
+    {
+      "epoch": 2.4267599475295145,
+      "grad_norm": 0.20130807161331177,
+      "learning_rate": 1.0981024137626923e-06,
+      "loss": 1.0507,
+      "step": 347
+    },
+    {
+      "epoch": 2.4337560122431134,
+      "grad_norm": 0.22717654705047607,
+      "learning_rate": 1.0727855884741057e-06,
+      "loss": 1.05,
+      "step": 348
+    },
+    {
+      "epoch": 2.440752076956712,
+      "grad_norm": 0.19452641904354095,
+      "learning_rate": 1.0477289033146675e-06,
+      "loss": 1.0433,
+      "step": 349
+    },
+    {
+      "epoch": 2.4477481416703104,
+      "grad_norm": 0.17928987741470337,
+      "learning_rate": 1.022934018048432e-06,
+      "loss": 1.0233,
+      "step": 350
+    },
+    {
+      "epoch": 2.454744206383909,
+      "grad_norm": 0.18564386665821075,
+      "learning_rate": 9.984025750977338e-07,
+      "loss": 1.0316,
+      "step": 351
+    },
+    {
+      "epoch": 2.461740271097508,
+      "grad_norm": 0.20213739573955536,
+      "learning_rate": 9.741361994343867e-07,
+      "loss": 1.0356,
+      "step": 352
+    },
+    {
+      "epoch": 2.4687363358111063,
+      "grad_norm": 0.19384591281414032,
+      "learning_rate": 9.501364984720557e-07,
+      "loss": 1.0086,
+      "step": 353
+    },
+    {
+      "epoch": 2.475732400524705,
+      "grad_norm": 0.1930152028799057,
+      "learning_rate": 9.264050619597697e-07,
+      "loss": 1.0246,
+      "step": 354
+    },
+    {
+      "epoch": 2.4827284652383033,
+      "grad_norm": 0.18979789316654205,
+      "learning_rate": 9.029434618766253e-07,
+      "loss": 0.9967,
+      "step": 355
+    },
+    {
+      "epoch": 2.489724529951902,
+      "grad_norm": 0.18281033635139465,
+      "learning_rate": 8.797532523276542e-07,
+      "loss": 1.0438,
+      "step": 356
+    },
+    {
+      "epoch": 2.4967205946655007,
+      "grad_norm": 0.18996168673038483,
+      "learning_rate": 8.56835969440879e-07,
+      "loss": 1.0244,
+      "step": 357
+    },
+    {
+      "epoch": 2.503716659379099,
+      "grad_norm": 0.1979200392961502,
+      "learning_rate": 8.341931312655582e-07,
+      "loss": 1.0317,
+      "step": 358
+    },
+    {
+      "epoch": 2.5107127240926976,
+      "grad_norm": 0.1972116082906723,
+      "learning_rate": 8.11826237671634e-07,
+      "loss": 1.0087,
+      "step": 359
+    },
+    {
+      "epoch": 2.5177087888062966,
+      "grad_norm": 0.18998436629772186,
+      "learning_rate": 7.897367702503755e-07,
+      "loss": 1.028,
+      "step": 360
+    },
+    {
+      "epoch": 2.524704853519895,
+      "grad_norm": 0.18390554189682007,
+      "learning_rate": 7.679261922162417e-07,
+      "loss": 1.0419,
+      "step": 361
+    },
+    {
+      "epoch": 2.5317009182334935,
+      "grad_norm": 0.18704506754875183,
+      "learning_rate": 7.463959483099547e-07,
+      "loss": 1.0043,
+      "step": 362
+    },
+    {
+      "epoch": 2.5386969829470925,
+      "grad_norm": 0.19950369000434875,
+      "learning_rate": 7.251474647028028e-07,
+      "loss": 1.0246,
+      "step": 363
+    },
+    {
+      "epoch": 2.545693047660691,
+      "grad_norm": 0.18810006976127625,
+      "learning_rate": 7.041821489021639e-07,
+      "loss": 0.9838,
+      "step": 364
+    },
+    {
+      "epoch": 2.5526891123742894,
+      "grad_norm": 0.18209373950958252,
+      "learning_rate": 6.835013896582821e-07,
+      "loss": 0.9988,
+      "step": 365
+    },
+    {
+      "epoch": 2.559685177087888,
+      "grad_norm": 0.16651113331317902,
+      "learning_rate": 6.631065568722633e-07,
+      "loss": 1.005,
+      "step": 366
+    },
+    {
+      "epoch": 2.566681241801487,
+      "grad_norm": 0.1969648152589798,
+      "learning_rate": 6.429990015053461e-07,
+      "loss": 1.0265,
+      "step": 367
+    },
+    {
+      "epoch": 2.5736773065150853,
+      "grad_norm": 0.1813141405582428,
+      "learning_rate": 6.231800554894029e-07,
+      "loss": 1.0341,
+      "step": 368
+    },
+    {
+      "epoch": 2.580673371228684,
+      "grad_norm": 0.1921863704919815,
+      "learning_rate": 6.036510316387196e-07,
+      "loss": 1.0168,
+      "step": 369
+    },
+    {
+      "epoch": 2.5876694359422823,
+      "grad_norm": 0.18890000879764557,
+      "learning_rate": 5.844132235630273e-07,
+      "loss": 1.0315,
+      "step": 370
+    },
+    {
+      "epoch": 2.594665500655881,
+      "grad_norm": 0.18416599929332733,
+      "learning_rate": 5.654679055818202e-07,
+      "loss": 1.0301,
+      "step": 371
+    },
+    {
+      "epoch": 2.6016615653694797,
+      "grad_norm": 0.18219484388828278,
+      "learning_rate": 5.46816332639939e-07,
+      "loss": 1.0354,
+      "step": 372
+    },
+    {
+      "epoch": 2.608657630083078,
+      "grad_norm": 0.19500690698623657,
+      "learning_rate": 5.284597402244457e-07,
+      "loss": 1.0644,
+      "step": 373
+    },
+    {
+      "epoch": 2.615653694796677,
+      "grad_norm": 0.19194085896015167,
+      "learning_rate": 5.103993442827832e-07,
+      "loss": 1.0283,
+      "step": 374
+    },
+    {
+      "epoch": 2.6226497595102756,
+      "grad_norm": 0.1873580813407898,
+      "learning_rate": 4.926363411422319e-07,
+      "loss": 1.0017,
+      "step": 375
+    },
+    {
+      "epoch": 2.629645824223874,
+      "grad_norm": 0.17427587509155273,
+      "learning_rate": 4.751719074306604e-07,
+      "loss": 1.0256,
+      "step": 376
+    },
+    {
+      "epoch": 2.6366418889374725,
+      "grad_norm": 0.1876949965953827,
+      "learning_rate": 4.58007199998593e-07,
+      "loss": 0.9952,
+      "step": 377
+    },
+    {
+      "epoch": 2.643637953651071,
+      "grad_norm": 0.18339499831199646,
+      "learning_rate": 4.4114335584256986e-07,
+      "loss": 1.021,
+      "step": 378
+    },
+    {
+      "epoch": 2.65063401836467,
+      "grad_norm": 0.1752660721540451,
+      "learning_rate": 4.2458149202984025e-07,
+      "loss": 1.0134,
+      "step": 379
+    },
+    {
+      "epoch": 2.6576300830782684,
+      "grad_norm": 0.17881804704666138,
+      "learning_rate": 4.0832270562436436e-07,
+      "loss": 1.0573,
+      "step": 380
+    },
+    {
+      "epoch": 2.664626147791867,
+      "grad_norm": 0.18826191127300262,
+      "learning_rate": 3.923680736141411e-07,
+      "loss": 1.0462,
+      "step": 381
+    },
+    {
+      "epoch": 2.671622212505466,
+      "grad_norm": 0.18888552486896515,
+      "learning_rate": 3.7671865283987254e-07,
+      "loss": 1.0385,
+      "step": 382
+    },
+    {
+      "epoch": 2.6786182772190643,
+      "grad_norm": 0.18031838536262512,
+      "learning_rate": 3.613754799249547e-07,
+      "loss": 1.0311,
+      "step": 383
+    },
+    {
+      "epoch": 2.685614341932663,
+      "grad_norm": 0.18545882403850555,
+      "learning_rate": 3.4633957120681294e-07,
+      "loss": 1.0288,
+      "step": 384
+    },
+    {
+      "epoch": 2.6926104066462617,
+      "grad_norm": 0.19693773984909058,
+      "learning_rate": 3.316119226695785e-07,
+      "loss": 1.0316,
+      "step": 385
+    },
+    {
+      "epoch": 2.69960647135986,
+      "grad_norm": 0.17951585352420807,
+      "learning_rate": 3.1719350987811537e-07,
+      "loss": 1.0237,
+      "step": 386
+    },
+    {
+      "epoch": 2.7066025360734587,
+      "grad_norm": 0.1714509278535843,
+      "learning_rate": 3.030852879133989e-07,
+      "loss": 1.0105,
+      "step": 387
+    },
+    {
+      "epoch": 2.713598600787057,
+      "grad_norm": 0.19598188996315002,
+      "learning_rate": 2.8928819130924656e-07,
+      "loss": 1.0337,
+      "step": 388
+    },
+    {
+      "epoch": 2.7205946655006557,
+      "grad_norm": 0.17747808992862701,
+      "learning_rate": 2.75803133990421e-07,
+      "loss": 1.0344,
+      "step": 389
+    },
+    {
+      "epoch": 2.7275907302142546,
+      "grad_norm": 0.18708738684654236,
+      "learning_rate": 2.6263100921208484e-07,
+      "loss": 1.0355,
+      "step": 390
+    },
+    {
+      "epoch": 2.734586794927853,
+      "grad_norm": 0.1784721165895462,
+      "learning_rate": 2.497726895006353e-07,
+      "loss": 1.0281,
+      "step": 391
+    },
+    {
+      "epoch": 2.7415828596414515,
+      "grad_norm": 0.18551653623580933,
+      "learning_rate": 2.3722902659590653e-07,
+      "loss": 1.0202,
+      "step": 392
+    },
+    {
+      "epoch": 2.7485789243550505,
+      "grad_norm": 0.17838101089000702,
+      "learning_rate": 2.2500085139474992e-07,
+      "loss": 0.9873,
+      "step": 393
+    },
+    {
+      "epoch": 2.755574989068649,
+      "grad_norm": 0.19315992295742035,
+      "learning_rate": 2.130889738959946e-07,
+      "loss": 1.0218,
+      "step": 394
+    },
+    {
+      "epoch": 2.7625710537822474,
+      "grad_norm": 0.18315425515174866,
+      "learning_rate": 2.0149418314679313e-07,
+      "loss": 1.0366,
+      "step": 395
+    },
+    {
+      "epoch": 2.7695671184958464,
+      "grad_norm": 0.17746944725513458,
+      "learning_rate": 1.902172471903563e-07,
+      "loss": 1.0194,
+      "step": 396
+    },
+    {
+      "epoch": 2.776563183209445,
+      "grad_norm": 0.185789555311203,
+      "learning_rate": 1.792589130150757e-07,
+      "loss": 1.0175,
+      "step": 397
+    },
+    {
+      "epoch": 2.7835592479230433,
+      "grad_norm": 0.18121521174907684,
+      "learning_rate": 1.6861990650504256e-07,
+      "loss": 1.0511,
+      "step": 398
+    },
+    {
+      "epoch": 2.790555312636642,
+      "grad_norm": 0.17998731136322021,
+      "learning_rate": 1.5830093239196765e-07,
+      "loss": 1.0307,
+      "step": 399
+    },
+    {
+      "epoch": 2.7975513773502403,
+      "grad_norm": 0.17075778543949127,
+      "learning_rate": 1.4830267420849587e-07,
+      "loss": 1.0304,
+      "step": 400
+    },
+    {
+      "epoch": 2.804547442063839,
+      "grad_norm": 0.18096929788589478,
+      "learning_rate": 1.3862579424293366e-07,
+      "loss": 1.0134,
+      "step": 401
+    },
+    {
+      "epoch": 2.8115435067774377,
+      "grad_norm": 0.1751806139945984,
+      "learning_rate": 1.292709334953729e-07,
+      "loss": 1.0119,
+      "step": 402
+    },
+    {
+      "epoch": 2.818539571491036,
+      "grad_norm": 0.18296852707862854,
+      "learning_rate": 1.202387116352355e-07,
+      "loss": 1.0188,
+      "step": 403
+    },
+    {
+      "epoch": 2.825535636204635,
+      "grad_norm": 0.18236733973026276,
+      "learning_rate": 1.1152972696022447e-07,
+      "loss": 1.0356,
+      "step": 404
+    },
+    {
+      "epoch": 2.8325317009182336,
+      "grad_norm": 0.17827041447162628,
+      "learning_rate": 1.0314455635669296e-07,
+      "loss": 1.0339,
+      "step": 405
+    },
+    {
+      "epoch": 2.839527765631832,
+      "grad_norm": 0.17066597938537598,
+      "learning_rate": 9.508375526142976e-08,
+      "loss": 1.0261,
+      "step": 406
+    },
+    {
+      "epoch": 2.8465238303454306,
+      "grad_norm": 0.1768139749765396,
+      "learning_rate": 8.734785762486875e-08,
+      "loss": 1.0479,
+      "step": 407
+    },
+    {
+      "epoch": 2.853519895059029,
+      "grad_norm": 0.16926994919776917,
+      "learning_rate": 7.993737587571825e-08,
+      "loss": 1.0307,
+      "step": 408
+    },
+    {
+      "epoch": 2.860515959772628,
+      "grad_norm": 0.17480771243572235,
+      "learning_rate": 7.285280088701996e-08,
+      "loss": 1.0116,
+      "step": 409
+    },
+    {
+      "epoch": 2.8675120244862264,
+      "grad_norm": 0.17737415432929993,
+      "learning_rate": 6.609460194362927e-08,
+      "loss": 1.0101,
+      "step": 410
+    },
+    {
+      "epoch": 2.874508089199825,
+      "grad_norm": 0.18863534927368164,
+      "learning_rate": 5.966322671113523e-08,
+      "loss": 1.0119,
+      "step": 411
+    },
+    {
+      "epoch": 2.881504153913424,
+      "grad_norm": 0.17490120232105255,
+      "learning_rate": 5.3559101206200337e-08,
+      "loss": 1.0334,
+      "step": 412
+    },
+    {
+      "epoch": 2.8885002186270223,
+      "grad_norm": 0.18111565709114075,
+      "learning_rate": 4.778262976834758e-08,
+      "loss": 1.0412,
+      "step": 413
+    },
+    {
+      "epoch": 2.895496283340621,
+      "grad_norm": 0.1804577261209488,
+      "learning_rate": 4.233419503317182e-08,
+      "loss": 1.0525,
+      "step": 414
+    },
+    {
+      "epoch": 2.9024923480542197,
+      "grad_norm": 0.16903232038021088,
+      "learning_rate": 3.7214157906996784e-08,
+      "loss": 1.016,
+      "step": 415
+    },
+    {
+      "epoch": 2.909488412767818,
+      "grad_norm": 0.17621533572673798,
+      "learning_rate": 3.242285754296859e-08,
+      "loss": 1.0176,
+      "step": 416
+    },
+    {
+      "epoch": 2.9164844774814167,
+      "grad_norm": 0.18803808093070984,
+      "learning_rate": 2.796061131858707e-08,
+      "loss": 1.0659,
+      "step": 417
+    },
+    {
+      "epoch": 2.923480542195015,
+      "grad_norm": 0.17898492515087128,
+      "learning_rate": 2.3827714814686488e-08,
+      "loss": 1.0179,
+      "step": 418
+    },
+    {
+      "epoch": 2.9304766069086137,
+      "grad_norm": 0.16611486673355103,
+      "learning_rate": 2.002444179585339e-08,
+      "loss": 1.0495,
+      "step": 419
+    },
+    {
+      "epoch": 2.9374726716222126,
+      "grad_norm": 0.1799437254667282,
+      "learning_rate": 1.655104419229281e-08,
+      "loss": 1.0172,
+      "step": 420
+    },
+    {
+      "epoch": 2.944468736335811,
+      "grad_norm": 0.17451150715351105,
+      "learning_rate": 1.3407752083142155e-08,
+      "loss": 1.0268,
+      "step": 421
+    },
+    {
+      "epoch": 2.9514648010494096,
+      "grad_norm": 0.17181828618049622,
+      "learning_rate": 1.059477368122841e-08,
+      "loss": 1.0194,
+      "step": 422
+    },
+    {
+      "epoch": 2.9584608657630085,
+      "grad_norm": 0.16880981624126434,
+      "learning_rate": 8.112295319276931e-09,
+      "loss": 1.0317,
+      "step": 423
+    },
+    {
+      "epoch": 2.965456930476607,
+      "grad_norm": 0.19107691943645477,
+      "learning_rate": 5.9604814375685546e-09,
+      "loss": 1.0622,
+      "step": 424
+    },
+    {
+      "epoch": 2.9724529951902054,
+      "grad_norm": 0.18856149911880493,
+      "learning_rate": 4.139474573047197e-09,
+      "loss": 1.0483,
+      "step": 425
+    },
+    {
+      "epoch": 2.9794490599038044,
+      "grad_norm": 0.18675896525382996,
+      "learning_rate": 2.6493953498790692e-09,
+      "loss": 1.0207,
+      "step": 426
+    },
+    {
+      "epoch": 2.986445124617403,
+      "grad_norm": 0.18428866565227509,
+      "learning_rate": 1.4903424714601821e-09,
+      "loss": 1.0299,
+      "step": 427
+    },
+    {
+      "epoch": 2.9934411893310013,
+      "grad_norm": 0.17121976613998413,
+      "learning_rate": 6.623927138804665e-10,
+      "loss": 1.0298,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.17932668328285217,
+      "learning_rate": 1.6560092083672818e-10,
+      "loss": 1.0303,
+      "step": 429
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 429,
+  "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": 2292626699059200.0,
+  "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 sha256:13e27dcab4b358594662fdc0823ac45133631773772244a04bd1751578fe4042
+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)