Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,73 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151662,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.54.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.54.1"
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bf281b4c8ff9c1eb92cc5ab950e0481d70e55182c50f51d16b8f69f984a865
+size 4684558368

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba0738c4c3bf1e95940f9accf2742eeea76c80069a360e61fbaa35f254be0bbd
+size 4676778920

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e951b6e52a167c13ac9c518e729c3249ca5c8b52c37fdffc66805eab845fd97
+size 4928480056

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e3846e2d3856dc0ce6ef2c4786e36c5d73d6b9355b5f94cc11390e3b6da869
+size 4928480080

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337d7d390651becff4972f0a190e7d7f4bb9945d4e66607c8e4bdccc8237d20e
+size 4676778952

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f940fb3d9ee98fe3ce9bde3dbbd2b852176797d4a6a536d9761158e52ce77eb7
+size 4928480096

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20419186fb99aec7dc559ea705342886db39e50afa1f343bede35a36f14d977c
+size 4928480096

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6291516e481fbb55eda3477622276b4ea07517917c87f1a2a774fabe9013586c
+size 4676778952

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d9252dd6c77465481618830353b728bfa6bb7f2002848e6abf579e70a21ec8
+size 4928480096

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ade73bfc6249e2439cfdd8c5167c54a5153a0045152c1bd709083a4e2674ea8
+size 4928480096

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c384649bf7e3ab91d589d62d0c50e7efb37f71942c8cb1f8295dd4bb6e7e5d0
+size 4676778952

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3233c0eecc7911a667ad7cf493bda4df971f2f9f85d554dd1ca8f33f2e5ec35
+size 2999075752

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:710586ae592871907c7fe3805a9f98d22fb328f15c0888343bcd9f1cc90a7e01
+size 3111649408

model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_parameters": 14768307200,
+    "total_size": 59073228800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00013-of-00013.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+    "model.norm.weight": "model-00012-of-00013.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fb5c6b773f4f8414a9f8d4f64f1059bab9c78cb9ecf1ff7c6ecdf2722964ce
+size 118146846556

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d744506ed8242dbe82c0f3357716f73248e5153ff68604326958faa28d9296
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bd68b4f78560921b755510e39aca8eb82d75911d689fb3466b01e5eb2040bc
+size 1465

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1370 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 10,
+  "global_step": 134,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0149812734082397,
+      "grad_norm": 6.645484924316406,
+      "learning_rate": 1e-05,
+      "loss": 1.6793,
+      "mean_token_accuracy": 0.6077414005994797,
+      "num_tokens": 7520.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.0299625468164794,
+      "grad_norm": 5.208061218261719,
+      "learning_rate": 9.96268656716418e-06,
+      "loss": 1.2004,
+      "mean_token_accuracy": 0.7127931267023087,
+      "num_tokens": 14631.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 4.237852573394775,
+      "learning_rate": 9.925373134328359e-06,
+      "loss": 1.3345,
+      "mean_token_accuracy": 0.6681558042764664,
+      "num_tokens": 21698.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.0599250936329588,
+      "grad_norm": 3.2547247409820557,
+      "learning_rate": 9.888059701492538e-06,
+      "loss": 1.0936,
+      "mean_token_accuracy": 0.7124579399824142,
+      "num_tokens": 29763.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 3.279022693634033,
+      "learning_rate": 9.850746268656717e-06,
+      "loss": 1.1485,
+      "mean_token_accuracy": 0.6985869109630585,
+      "num_tokens": 36572.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 3.9445199966430664,
+      "learning_rate": 9.813432835820897e-06,
+      "loss": 1.2735,
+      "mean_token_accuracy": 0.6686816662549973,
+      "num_tokens": 42969.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.10486891385767791,
+      "grad_norm": 3.1979117393493652,
+      "learning_rate": 9.776119402985076e-06,
+      "loss": 1.1807,
+      "mean_token_accuracy": 0.6792618632316589,
+      "num_tokens": 49628.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.1198501872659176,
+      "grad_norm": 2.979384183883667,
+      "learning_rate": 9.738805970149255e-06,
+      "loss": 1.1305,
+      "mean_token_accuracy": 0.6916055679321289,
+      "num_tokens": 57634.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 4.175307750701904,
+      "learning_rate": 9.701492537313434e-06,
+      "loss": 1.1587,
+      "mean_token_accuracy": 0.6850023865699768,
+      "num_tokens": 64493.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.149812734082397,
+      "grad_norm": 3.318324565887451,
+      "learning_rate": 9.664179104477612e-06,
+      "loss": 1.2182,
+      "mean_token_accuracy": 0.666175588965416,
+      "num_tokens": 71062.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.149812734082397,
+      "eval_loss": 1.1548303365707397,
+      "eval_mean_token_accuracy": 0.6638695597648621,
+      "eval_num_tokens": 71062.0,
+      "eval_runtime": 43.4636,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 10
+    },
+    {
+      "epoch": 0.1647940074906367,
+      "grad_norm": 3.0939977169036865,
+      "learning_rate": 9.626865671641792e-06,
+      "loss": 1.0469,
+      "mean_token_accuracy": 0.7054508179426193,
+      "num_tokens": 78715.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 3.1718571186065674,
+      "learning_rate": 9.589552238805972e-06,
+      "loss": 0.9968,
+      "mean_token_accuracy": 0.7284530699253082,
+      "num_tokens": 86684.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.1947565543071161,
+      "grad_norm": 2.906012535095215,
+      "learning_rate": 9.552238805970149e-06,
+      "loss": 1.0074,
+      "mean_token_accuracy": 0.7302294373512268,
+      "num_tokens": 94023.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.20973782771535582,
+      "grad_norm": 3.084291458129883,
+      "learning_rate": 9.51492537313433e-06,
+      "loss": 1.096,
+      "mean_token_accuracy": 0.6945489645004272,
+      "num_tokens": 101018.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 3.168394088745117,
+      "learning_rate": 9.477611940298507e-06,
+      "loss": 1.1981,
+      "mean_token_accuracy": 0.6750565618276596,
+      "num_tokens": 108576.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.2397003745318352,
+      "grad_norm": 3.0310959815979004,
+      "learning_rate": 9.440298507462688e-06,
+      "loss": 1.2195,
+      "mean_token_accuracy": 0.6774358600378036,
+      "num_tokens": 116231.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.2546816479400749,
+      "grad_norm": 3.1885411739349365,
+      "learning_rate": 9.402985074626867e-06,
+      "loss": 1.1123,
+      "mean_token_accuracy": 0.6851049065589905,
+      "num_tokens": 122820.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 2.9225549697875977,
+      "learning_rate": 9.365671641791045e-06,
+      "loss": 1.1255,
+      "mean_token_accuracy": 0.6796696484088898,
+      "num_tokens": 130744.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.2846441947565543,
+      "grad_norm": 3.281294345855713,
+      "learning_rate": 9.328358208955226e-06,
+      "loss": 1.1157,
+      "mean_token_accuracy": 0.6871359646320343,
+      "num_tokens": 137441.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.299625468164794,
+      "grad_norm": 3.2192912101745605,
+      "learning_rate": 9.291044776119403e-06,
+      "loss": 1.3184,
+      "mean_token_accuracy": 0.6449258774518967,
+      "num_tokens": 143961.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.299625468164794,
+      "eval_loss": 1.0996215343475342,
+      "eval_mean_token_accuracy": 0.6732441584269205,
+      "eval_num_tokens": 143961.0,
+      "eval_runtime": 43.4644,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 20
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": 2.8447461128234863,
+      "learning_rate": 9.253731343283582e-06,
+      "loss": 0.8826,
+      "mean_token_accuracy": 0.7349306046962738,
+      "num_tokens": 150885.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.3295880149812734,
+      "grad_norm": 2.926057815551758,
+      "learning_rate": 9.216417910447763e-06,
+      "loss": 0.958,
+      "mean_token_accuracy": 0.7313619703054428,
+      "num_tokens": 157876.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.3445692883895131,
+      "grad_norm": 3.294577121734619,
+      "learning_rate": 9.17910447761194e-06,
+      "loss": 1.1452,
+      "mean_token_accuracy": 0.6808282732963562,
+      "num_tokens": 165203.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 3.026679515838623,
+      "learning_rate": 9.14179104477612e-06,
+      "loss": 1.0559,
+      "mean_token_accuracy": 0.7152852565050125,
+      "num_tokens": 171790.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.37453183520599254,
+      "grad_norm": 2.5701076984405518,
+      "learning_rate": 9.104477611940299e-06,
+      "loss": 0.8404,
+      "mean_token_accuracy": 0.755279466509819,
+      "num_tokens": 179560.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.3895131086142322,
+      "grad_norm": 2.930906295776367,
+      "learning_rate": 9.067164179104478e-06,
+      "loss": 1.0629,
+      "mean_token_accuracy": 0.6979093104600906,
+      "num_tokens": 187129.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 2.5857908725738525,
+      "learning_rate": 9.029850746268657e-06,
+      "loss": 0.9093,
+      "mean_token_accuracy": 0.7412554323673248,
+      "num_tokens": 194238.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.41947565543071164,
+      "grad_norm": 2.9247360229492188,
+      "learning_rate": 8.992537313432836e-06,
+      "loss": 1.0202,
+      "mean_token_accuracy": 0.7101631760597229,
+      "num_tokens": 201176.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.4344569288389513,
+      "grad_norm": 3.2126927375793457,
+      "learning_rate": 8.955223880597016e-06,
+      "loss": 1.1267,
+      "mean_token_accuracy": 0.6963846385478973,
+      "num_tokens": 207843.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 2.6786251068115234,
+      "learning_rate": 8.917910447761195e-06,
+      "loss": 0.9444,
+      "mean_token_accuracy": 0.7381020188331604,
+      "num_tokens": 215058.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.449438202247191,
+      "eval_loss": 1.0702282190322876,
+      "eval_mean_token_accuracy": 0.6778951783974966,
+      "eval_num_tokens": 215058.0,
+      "eval_runtime": 43.4996,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 30
+    },
+    {
+      "epoch": 0.46441947565543074,
+      "grad_norm": 3.422229528427124,
+      "learning_rate": 8.880597014925374e-06,
+      "loss": 1.1104,
+      "mean_token_accuracy": 0.6989456862211227,
+      "num_tokens": 220989.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.4794007490636704,
+      "grad_norm": 2.9094724655151367,
+      "learning_rate": 8.843283582089553e-06,
+      "loss": 0.9101,
+      "mean_token_accuracy": 0.7397958487272263,
+      "num_tokens": 228235.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 2.905221700668335,
+      "learning_rate": 8.805970149253732e-06,
+      "loss": 0.9017,
+      "mean_token_accuracy": 0.739780843257904,
+      "num_tokens": 235497.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.5093632958801498,
+      "grad_norm": 2.7689316272735596,
+      "learning_rate": 8.768656716417911e-06,
+      "loss": 0.8806,
+      "mean_token_accuracy": 0.7460598647594452,
+      "num_tokens": 242951.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.5243445692883895,
+      "grad_norm": 2.711458683013916,
+      "learning_rate": 8.73134328358209e-06,
+      "loss": 0.9845,
+      "mean_token_accuracy": 0.7096125036478043,
+      "num_tokens": 250554.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 2.9433722496032715,
+      "learning_rate": 8.69402985074627e-06,
+      "loss": 0.9512,
+      "mean_token_accuracy": 0.7236437946557999,
+      "num_tokens": 258167.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.5543071161048689,
+      "grad_norm": 3.174933910369873,
+      "learning_rate": 8.656716417910447e-06,
+      "loss": 1.075,
+      "mean_token_accuracy": 0.6945899575948715,
+      "num_tokens": 265000.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.5692883895131086,
+      "grad_norm": 2.713667392730713,
+      "learning_rate": 8.619402985074628e-06,
+      "loss": 0.8271,
+      "mean_token_accuracy": 0.7603205889463425,
+      "num_tokens": 272757.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 2.6623470783233643,
+      "learning_rate": 8.582089552238807e-06,
+      "loss": 0.8481,
+      "mean_token_accuracy": 0.7493215799331665,
+      "num_tokens": 280232.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.599250936329588,
+      "grad_norm": 2.6669371128082275,
+      "learning_rate": 8.544776119402986e-06,
+      "loss": 1.0571,
+      "mean_token_accuracy": 0.6984888315200806,
+      "num_tokens": 287844.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.599250936329588,
+      "eval_loss": 1.0412267446517944,
+      "eval_mean_token_accuracy": 0.6823226809501648,
+      "eval_num_tokens": 287844.0,
+      "eval_runtime": 43.4294,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 40
+    },
+    {
+      "epoch": 0.6142322097378277,
+      "grad_norm": 2.81078839302063,
+      "learning_rate": 8.507462686567165e-06,
+      "loss": 0.8895,
+      "mean_token_accuracy": 0.7473254799842834,
+      "num_tokens": 294955.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 2.718947649002075,
+      "learning_rate": 8.470149253731343e-06,
+      "loss": 0.9208,
+      "mean_token_accuracy": 0.7264387309551239,
+      "num_tokens": 302360.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.6441947565543071,
+      "grad_norm": 2.797668933868408,
+      "learning_rate": 8.432835820895524e-06,
+      "loss": 1.0173,
+      "mean_token_accuracy": 0.7081942111253738,
+      "num_tokens": 309893.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.6591760299625468,
+      "grad_norm": 3.0845787525177,
+      "learning_rate": 8.395522388059703e-06,
+      "loss": 1.0575,
+      "mean_token_accuracy": 0.7010719627141953,
+      "num_tokens": 316759.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 2.764462947845459,
+      "learning_rate": 8.35820895522388e-06,
+      "loss": 1.1272,
+      "mean_token_accuracy": 0.6816393285989761,
+      "num_tokens": 324600.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.6891385767790262,
+      "grad_norm": 2.4682984352111816,
+      "learning_rate": 8.320895522388061e-06,
+      "loss": 0.797,
+      "mean_token_accuracy": 0.7550250142812729,
+      "num_tokens": 331644.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.704119850187266,
+      "grad_norm": 2.796246290206909,
+      "learning_rate": 8.283582089552239e-06,
+      "loss": 1.0701,
+      "mean_token_accuracy": 0.6996825039386749,
+      "num_tokens": 338637.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 2.880173921585083,
+      "learning_rate": 8.246268656716418e-06,
+      "loss": 1.1005,
+      "mean_token_accuracy": 0.6946816593408585,
+      "num_tokens": 345963.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.7340823970037453,
+      "grad_norm": 2.7749922275543213,
+      "learning_rate": 8.208955223880599e-06,
+      "loss": 0.9123,
+      "mean_token_accuracy": 0.7341801673173904,
+      "num_tokens": 353032.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.7490636704119851,
+      "grad_norm": 2.716906785964966,
+      "learning_rate": 8.171641791044776e-06,
+      "loss": 0.9649,
+      "mean_token_accuracy": 0.7190811187028885,
+      "num_tokens": 360374.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.7490636704119851,
+      "eval_loss": 1.0224930047988892,
+      "eval_mean_token_accuracy": 0.6871222953001658,
+      "eval_num_tokens": 360374.0,
+      "eval_runtime": 43.4776,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 50
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 2.576030731201172,
+      "learning_rate": 8.134328358208955e-06,
+      "loss": 0.9832,
+      "mean_token_accuracy": 0.7258175909519196,
+      "num_tokens": 367529.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.7790262172284644,
+      "grad_norm": 2.765681743621826,
+      "learning_rate": 8.097014925373135e-06,
+      "loss": 0.9807,
+      "mean_token_accuracy": 0.7210909426212311,
+      "num_tokens": 374472.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.7940074906367042,
+      "grad_norm": 2.5107247829437256,
+      "learning_rate": 8.059701492537314e-06,
+      "loss": 0.86,
+      "mean_token_accuracy": 0.7453574240207672,
+      "num_tokens": 382443.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 2.511554479598999,
+      "learning_rate": 8.022388059701493e-06,
+      "loss": 0.9156,
+      "mean_token_accuracy": 0.7413896918296814,
+      "num_tokens": 389998.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.8239700374531835,
+      "grad_norm": 2.9105887413024902,
+      "learning_rate": 7.985074626865672e-06,
+      "loss": 0.8634,
+      "mean_token_accuracy": 0.7419312596321106,
+      "num_tokens": 396698.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.8389513108614233,
+      "grad_norm": 2.4456405639648438,
+      "learning_rate": 7.947761194029851e-06,
+      "loss": 0.8547,
+      "mean_token_accuracy": 0.7464274764060974,
+      "num_tokens": 403984.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 3.117522716522217,
+      "learning_rate": 7.91044776119403e-06,
+      "loss": 1.0601,
+      "mean_token_accuracy": 0.6881874799728394,
+      "num_tokens": 411433.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.8689138576779026,
+      "grad_norm": 2.4795329570770264,
+      "learning_rate": 7.87313432835821e-06,
+      "loss": 0.8548,
+      "mean_token_accuracy": 0.7407911419868469,
+      "num_tokens": 418859.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.8838951310861424,
+      "grad_norm": 3.0380287170410156,
+      "learning_rate": 7.835820895522389e-06,
+      "loss": 1.0231,
+      "mean_token_accuracy": 0.7012683600187302,
+      "num_tokens": 425440.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 2.596809148788452,
+      "learning_rate": 7.798507462686568e-06,
+      "loss": 0.9533,
+      "mean_token_accuracy": 0.7234554290771484,
+      "num_tokens": 432346.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.898876404494382,
+      "eval_loss": 1.0079383850097656,
+      "eval_mean_token_accuracy": 0.6899242699146271,
+      "eval_num_tokens": 432346.0,
+      "eval_runtime": 43.4508,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 60
+    },
+    {
+      "epoch": 0.9138576779026217,
+      "grad_norm": 2.8112661838531494,
+      "learning_rate": 7.761194029850747e-06,
+      "loss": 0.9786,
+      "mean_token_accuracy": 0.7173863798379898,
+      "num_tokens": 440164.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.9288389513108615,
+      "grad_norm": 3.0009336471557617,
+      "learning_rate": 7.723880597014926e-06,
+      "loss": 1.1157,
+      "mean_token_accuracy": 0.6876846700906754,
+      "num_tokens": 446900.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 2.882216215133667,
+      "learning_rate": 7.686567164179105e-06,
+      "loss": 0.9868,
+      "mean_token_accuracy": 0.7076680213212967,
+      "num_tokens": 454043.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.9588014981273408,
+      "grad_norm": 2.567683219909668,
+      "learning_rate": 7.649253731343284e-06,
+      "loss": 0.8569,
+      "mean_token_accuracy": 0.7410573810338974,
+      "num_tokens": 461616.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.9737827715355806,
+      "grad_norm": 2.8576714992523193,
+      "learning_rate": 7.611940298507463e-06,
+      "loss": 1.0125,
+      "mean_token_accuracy": 0.7113172262907028,
+      "num_tokens": 469118.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 2.429183006286621,
+      "learning_rate": 7.574626865671643e-06,
+      "loss": 0.8176,
+      "mean_token_accuracy": 0.7573917061090469,
+      "num_tokens": 476582.0,
+      "step": 66
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.128382444381714,
+      "learning_rate": 7.537313432835821e-06,
+      "loss": 0.8825,
+      "mean_token_accuracy": 0.7674418290456136,
+      "num_tokens": 480934.0,
+      "step": 67
+    },
+    {
+      "epoch": 1.0149812734082397,
+      "grad_norm": 2.555082321166992,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.6467,
+      "mean_token_accuracy": 0.7994843870401382,
+      "num_tokens": 488505.0,
+      "step": 68
+    },
+    {
+      "epoch": 1.0299625468164795,
+      "grad_norm": 2.6702513694763184,
+      "learning_rate": 7.46268656716418e-06,
+      "loss": 0.6819,
+      "mean_token_accuracy": 0.8006551265716553,
+      "num_tokens": 495367.0,
+      "step": 69
+    },
+    {
+      "epoch": 1.0449438202247192,
+      "grad_norm": 2.4463446140289307,
+      "learning_rate": 7.4253731343283585e-06,
+      "loss": 0.6766,
+      "mean_token_accuracy": 0.7914196252822876,
+      "num_tokens": 502801.0,
+      "step": 70
+    },
+    {
+      "epoch": 1.0449438202247192,
+      "eval_loss": 1.000529408454895,
+      "eval_mean_token_accuracy": 0.6923578282197317,
+      "eval_num_tokens": 502801.0,
+      "eval_runtime": 43.4456,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 70
+    },
+    {
+      "epoch": 1.0599250936329587,
+      "grad_norm": 2.083836793899536,
+      "learning_rate": 7.3880597014925385e-06,
+      "loss": 0.5576,
+      "mean_token_accuracy": 0.830506294965744,
+      "num_tokens": 509852.0,
+      "step": 71
+    },
+    {
+      "epoch": 1.0749063670411985,
+      "grad_norm": 2.3526670932769775,
+      "learning_rate": 7.350746268656717e-06,
+      "loss": 0.6305,
+      "mean_token_accuracy": 0.8095849454402924,
+      "num_tokens": 517474.0,
+      "step": 72
+    },
+    {
+      "epoch": 1.0898876404494382,
+      "grad_norm": 2.429677724838257,
+      "learning_rate": 7.313432835820896e-06,
+      "loss": 0.6376,
+      "mean_token_accuracy": 0.8020687401294708,
+      "num_tokens": 524332.0,
+      "step": 73
+    },
+    {
+      "epoch": 1.104868913857678,
+      "grad_norm": 2.212477445602417,
+      "learning_rate": 7.276119402985076e-06,
+      "loss": 0.5534,
+      "mean_token_accuracy": 0.8321953117847443,
+      "num_tokens": 531739.0,
+      "step": 74
+    },
+    {
+      "epoch": 1.1198501872659177,
+      "grad_norm": 2.5952513217926025,
+      "learning_rate": 7.238805970149254e-06,
+      "loss": 0.6081,
+      "mean_token_accuracy": 0.8088606148958206,
+      "num_tokens": 538384.0,
+      "step": 75
+    },
+    {
+      "epoch": 1.1348314606741572,
+      "grad_norm": 2.4394075870513916,
+      "learning_rate": 7.2014925373134335e-06,
+      "loss": 0.5225,
+      "mean_token_accuracy": 0.8409454524517059,
+      "num_tokens": 546061.0,
+      "step": 76
+    },
+    {
+      "epoch": 1.149812734082397,
+      "grad_norm": 2.3486266136169434,
+      "learning_rate": 7.164179104477612e-06,
+      "loss": 0.6461,
+      "mean_token_accuracy": 0.8038217276334763,
+      "num_tokens": 553550.0,
+      "step": 77
+    },
+    {
+      "epoch": 1.1647940074906367,
+      "grad_norm": 2.2467193603515625,
+      "learning_rate": 7.126865671641792e-06,
+      "loss": 0.5553,
+      "mean_token_accuracy": 0.8217796683311462,
+      "num_tokens": 560708.0,
+      "step": 78
+    },
+    {
+      "epoch": 1.1797752808988764,
+      "grad_norm": 2.407600164413452,
+      "learning_rate": 7.089552238805971e-06,
+      "loss": 0.5811,
+      "mean_token_accuracy": 0.8181268125772476,
+      "num_tokens": 567407.0,
+      "step": 79
+    },
+    {
+      "epoch": 1.1947565543071161,
+      "grad_norm": 2.376070737838745,
+      "learning_rate": 7.052238805970149e-06,
+      "loss": 0.5261,
+      "mean_token_accuracy": 0.8382349163293839,
+      "num_tokens": 574718.0,
+      "step": 80
+    },
+    {
+      "epoch": 1.1947565543071161,
+      "eval_loss": 1.0289438962936401,
+      "eval_mean_token_accuracy": 0.6871420840422312,
+      "eval_num_tokens": 574718.0,
+      "eval_runtime": 43.4624,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 80
+    },
+    {
+      "epoch": 1.2097378277153559,
+      "grad_norm": 2.738510847091675,
+      "learning_rate": 7.014925373134329e-06,
+      "loss": 0.6841,
+      "mean_token_accuracy": 0.7840229570865631,
+      "num_tokens": 581276.0,
+      "step": 81
+    },
+    {
+      "epoch": 1.2247191011235956,
+      "grad_norm": 2.3343069553375244,
+      "learning_rate": 6.9776119402985076e-06,
+      "loss": 0.5493,
+      "mean_token_accuracy": 0.8304655849933624,
+      "num_tokens": 588904.0,
+      "step": 82
+    },
+    {
+      "epoch": 1.2397003745318351,
+      "grad_norm": 2.639784336090088,
+      "learning_rate": 6.9402985074626876e-06,
+      "loss": 0.6857,
+      "mean_token_accuracy": 0.7973657697439194,
+      "num_tokens": 595858.0,
+      "step": 83
+    },
+    {
+      "epoch": 1.2546816479400749,
+      "grad_norm": 2.3760740756988525,
+      "learning_rate": 6.902985074626867e-06,
+      "loss": 0.5136,
+      "mean_token_accuracy": 0.8422924876213074,
+      "num_tokens": 602581.0,
+      "step": 84
+    },
+    {
+      "epoch": 1.2696629213483146,
+      "grad_norm": 2.2667794227600098,
+      "learning_rate": 6.865671641791045e-06,
+      "loss": 0.5062,
+      "mean_token_accuracy": 0.83640918135643,
+      "num_tokens": 609750.0,
+      "step": 85
+    },
+    {
+      "epoch": 1.2846441947565543,
+      "grad_norm": 2.4145731925964355,
+      "learning_rate": 6.828358208955225e-06,
+      "loss": 0.653,
+      "mean_token_accuracy": 0.7934205830097198,
+      "num_tokens": 617577.0,
+      "step": 86
+    },
+    {
+      "epoch": 1.299625468164794,
+      "grad_norm": 2.5289885997772217,
+      "learning_rate": 6.791044776119403e-06,
+      "loss": 0.5714,
+      "mean_token_accuracy": 0.8144723027944565,
+      "num_tokens": 623717.0,
+      "step": 87
+    },
+    {
+      "epoch": 1.3146067415730336,
+      "grad_norm": 2.1667280197143555,
+      "learning_rate": 6.7537313432835825e-06,
+      "loss": 0.5032,
+      "mean_token_accuracy": 0.8375886827707291,
+      "num_tokens": 631372.0,
+      "step": 88
+    },
+    {
+      "epoch": 1.3295880149812733,
+      "grad_norm": 2.4753546714782715,
+      "learning_rate": 6.7164179104477625e-06,
+      "loss": 0.5357,
+      "mean_token_accuracy": 0.8220501989126205,
+      "num_tokens": 637531.0,
+      "step": 89
+    },
+    {
+      "epoch": 1.344569288389513,
+      "grad_norm": 2.417269706726074,
+      "learning_rate": 6.679104477611941e-06,
+      "loss": 0.5053,
+      "mean_token_accuracy": 0.8365453034639359,
+      "num_tokens": 643953.0,
+      "step": 90
+    },
+    {
+      "epoch": 1.344569288389513,
+      "eval_loss": 1.043993592262268,
+      "eval_mean_token_accuracy": 0.6838832795619965,
+      "eval_num_tokens": 643953.0,
+      "eval_runtime": 43.4519,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 90
+    },
+    {
+      "epoch": 1.3595505617977528,
+      "grad_norm": 2.4452741146087646,
+      "learning_rate": 6.64179104477612e-06,
+      "loss": 0.5959,
+      "mean_token_accuracy": 0.8205520063638687,
+      "num_tokens": 650371.0,
+      "step": 91
+    },
+    {
+      "epoch": 1.3745318352059925,
+      "grad_norm": 2.4637227058410645,
+      "learning_rate": 6.604477611940298e-06,
+      "loss": 0.609,
+      "mean_token_accuracy": 0.8141357600688934,
+      "num_tokens": 657701.0,
+      "step": 92
+    },
+    {
+      "epoch": 1.3895131086142323,
+      "grad_norm": 2.5266008377075195,
+      "learning_rate": 6.567164179104478e-06,
+      "loss": 0.5932,
+      "mean_token_accuracy": 0.8143609464168549,
+      "num_tokens": 665322.0,
+      "step": 93
+    },
+    {
+      "epoch": 1.404494382022472,
+      "grad_norm": 2.3636891841888428,
+      "learning_rate": 6.5298507462686575e-06,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.8084951192140579,
+      "num_tokens": 672852.0,
+      "step": 94
+    },
+    {
+      "epoch": 1.4194756554307117,
+      "grad_norm": 2.303436756134033,
+      "learning_rate": 6.492537313432837e-06,
+      "loss": 0.4828,
+      "mean_token_accuracy": 0.8466101735830307,
+      "num_tokens": 679760.0,
+      "step": 95
+    },
+    {
+      "epoch": 1.4344569288389513,
+      "grad_norm": 2.34370493888855,
+      "learning_rate": 6.455223880597016e-06,
+      "loss": 0.5763,
+      "mean_token_accuracy": 0.8200996369123459,
+      "num_tokens": 686791.0,
+      "step": 96
+    },
+    {
+      "epoch": 1.449438202247191,
+      "grad_norm": 2.2648942470550537,
+      "learning_rate": 6.417910447761194e-06,
+      "loss": 0.4666,
+      "mean_token_accuracy": 0.8406203389167786,
+      "num_tokens": 693028.0,
+      "step": 97
+    },
+    {
+      "epoch": 1.4644194756554307,
+      "grad_norm": 2.3541007041931152,
+      "learning_rate": 6.380597014925374e-06,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.8213587552309036,
+      "num_tokens": 701220.0,
+      "step": 98
+    },
+    {
+      "epoch": 1.4794007490636705,
+      "grad_norm": 2.1910910606384277,
+      "learning_rate": 6.343283582089553e-06,
+      "loss": 0.5371,
+      "mean_token_accuracy": 0.8270279318094254,
+      "num_tokens": 709016.0,
+      "step": 99
+    },
+    {
+      "epoch": 1.49438202247191,
+      "grad_norm": 2.215508460998535,
+      "learning_rate": 6.3059701492537316e-06,
+      "loss": 0.5577,
+      "mean_token_accuracy": 0.8273791819810867,
+      "num_tokens": 716500.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.49438202247191,
+      "eval_loss": 1.0362759828567505,
+      "eval_mean_token_accuracy": 0.6868139902750651,
+      "eval_num_tokens": 716500.0,
+      "eval_runtime": 43.4907,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 100
+    },
+    {
+      "epoch": 1.5093632958801497,
+      "grad_norm": 2.368717908859253,
+      "learning_rate": 6.2686567164179116e-06,
+      "loss": 0.5906,
+      "mean_token_accuracy": 0.817937821149826,
+      "num_tokens": 723654.0,
+      "step": 101
+    },
+    {
+      "epoch": 1.5243445692883895,
+      "grad_norm": 2.5242090225219727,
+      "learning_rate": 6.23134328358209e-06,
+      "loss": 0.6044,
+      "mean_token_accuracy": 0.8119681477546692,
+      "num_tokens": 730772.0,
+      "step": 102
+    },
+    {
+      "epoch": 1.5393258426966292,
+      "grad_norm": 2.181792736053467,
+      "learning_rate": 6.194029850746269e-06,
+      "loss": 0.5103,
+      "mean_token_accuracy": 0.8396165817975998,
+      "num_tokens": 737800.0,
+      "step": 103
+    },
+    {
+      "epoch": 1.554307116104869,
+      "grad_norm": 2.560577392578125,
+      "learning_rate": 6.156716417910447e-06,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.8078210204839706,
+      "num_tokens": 744874.0,
+      "step": 104
+    },
+    {
+      "epoch": 1.5692883895131087,
+      "grad_norm": 2.102379322052002,
+      "learning_rate": 6.119402985074627e-06,
+      "loss": 0.4746,
+      "mean_token_accuracy": 0.8518716990947723,
+      "num_tokens": 752448.0,
+      "step": 105
+    },
+    {
+      "epoch": 1.5842696629213484,
+      "grad_norm": 2.304199695587158,
+      "learning_rate": 6.0820895522388065e-06,
+      "loss": 0.5656,
+      "mean_token_accuracy": 0.8216982781887054,
+      "num_tokens": 759899.0,
+      "step": 106
+    },
+    {
+      "epoch": 1.5992509363295881,
+      "grad_norm": 2.216642141342163,
+      "learning_rate": 6.044776119402986e-06,
+      "loss": 0.5291,
+      "mean_token_accuracy": 0.8351717591285706,
+      "num_tokens": 768016.0,
+      "step": 107
+    },
+    {
+      "epoch": 1.6142322097378277,
+      "grad_norm": 2.435307264328003,
+      "learning_rate": 6.007462686567165e-06,
+      "loss": 0.6234,
+      "mean_token_accuracy": 0.8072042167186737,
+      "num_tokens": 775450.0,
+      "step": 108
+    },
+    {
+      "epoch": 1.6292134831460674,
+      "grad_norm": 2.4394967555999756,
+      "learning_rate": 5.970149253731343e-06,
+      "loss": 0.5309,
+      "mean_token_accuracy": 0.8372008353471756,
+      "num_tokens": 782761.0,
+      "step": 109
+    },
+    {
+      "epoch": 1.6441947565543071,
+      "grad_norm": 2.545595645904541,
+      "learning_rate": 5.932835820895523e-06,
+      "loss": 0.6327,
+      "mean_token_accuracy": 0.8080395758152008,
+      "num_tokens": 789777.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.6441947565543071,
+      "eval_loss": 1.0350403785705566,
+      "eval_mean_token_accuracy": 0.6877939999103546,
+      "eval_num_tokens": 789777.0,
+      "eval_runtime": 43.499,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 110
+    },
+    {
+      "epoch": 1.6591760299625467,
+      "grad_norm": 2.6292037963867188,
+      "learning_rate": 5.895522388059702e-06,
+      "loss": 0.5986,
+      "mean_token_accuracy": 0.8076180070638657,
+      "num_tokens": 797195.0,
+      "step": 111
+    },
+    {
+      "epoch": 1.6741573033707864,
+      "grad_norm": 2.416217803955078,
+      "learning_rate": 5.858208955223881e-06,
+      "loss": 0.5786,
+      "mean_token_accuracy": 0.819035142660141,
+      "num_tokens": 803750.0,
+      "step": 112
+    },
+    {
+      "epoch": 1.6891385767790261,
+      "grad_norm": 2.511836528778076,
+      "learning_rate": 5.820895522388061e-06,
+      "loss": 0.6348,
+      "mean_token_accuracy": 0.8027018457651138,
+      "num_tokens": 811335.0,
+      "step": 113
+    },
+    {
+      "epoch": 1.7041198501872659,
+      "grad_norm": 2.4908852577209473,
+      "learning_rate": 5.783582089552239e-06,
+      "loss": 0.7,
+      "mean_token_accuracy": 0.789110392332077,
+      "num_tokens": 818745.0,
+      "step": 114
+    },
+    {
+      "epoch": 1.7191011235955056,
+      "grad_norm": 2.6129393577575684,
+      "learning_rate": 5.746268656716418e-06,
+      "loss": 0.5622,
+      "mean_token_accuracy": 0.8225392550230026,
+      "num_tokens": 826035.0,
+      "step": 115
+    },
+    {
+      "epoch": 1.7340823970037453,
+      "grad_norm": 2.579789638519287,
+      "learning_rate": 5.708955223880598e-06,
+      "loss": 0.7188,
+      "mean_token_accuracy": 0.7761909365653992,
+      "num_tokens": 833714.0,
+      "step": 116
+    },
+    {
+      "epoch": 1.749063670411985,
+      "grad_norm": 2.415377616882324,
+      "learning_rate": 5.671641791044776e-06,
+      "loss": 0.5946,
+      "mean_token_accuracy": 0.8112916648387909,
+      "num_tokens": 840530.0,
+      "step": 117
+    },
+    {
+      "epoch": 1.7640449438202248,
+      "grad_norm": 2.317101001739502,
+      "learning_rate": 5.6343283582089556e-06,
+      "loss": 0.5669,
+      "mean_token_accuracy": 0.8185659945011139,
+      "num_tokens": 847520.0,
+      "step": 118
+    },
+    {
+      "epoch": 1.7790262172284645,
+      "grad_norm": 2.222646474838257,
+      "learning_rate": 5.597014925373134e-06,
+      "loss": 0.5257,
+      "mean_token_accuracy": 0.8318661004304886,
+      "num_tokens": 854801.0,
+      "step": 119
+    },
+    {
+      "epoch": 1.7940074906367043,
+      "grad_norm": 2.343552589416504,
+      "learning_rate": 5.559701492537314e-06,
+      "loss": 0.6078,
+      "mean_token_accuracy": 0.8209575116634369,
+      "num_tokens": 861837.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.7940074906367043,
+      "eval_loss": 1.0262762308120728,
+      "eval_mean_token_accuracy": 0.6882797876993815,
+      "eval_num_tokens": 861837.0,
+      "eval_runtime": 43.4358,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 120
+    },
+    {
+      "epoch": 1.8089887640449438,
+      "grad_norm": 2.282057762145996,
+      "learning_rate": 5.522388059701493e-06,
+      "loss": 0.5822,
+      "mean_token_accuracy": 0.8263915479183197,
+      "num_tokens": 868898.0,
+      "step": 121
+    },
+    {
+      "epoch": 1.8239700374531835,
+      "grad_norm": 2.2916383743286133,
+      "learning_rate": 5.485074626865672e-06,
+      "loss": 0.4774,
+      "mean_token_accuracy": 0.8558280915021896,
+      "num_tokens": 875927.0,
+      "step": 122
+    },
+    {
+      "epoch": 1.8389513108614233,
+      "grad_norm": 2.3634865283966064,
+      "learning_rate": 5.447761194029851e-06,
+      "loss": 0.5833,
+      "mean_token_accuracy": 0.8178814053535461,
+      "num_tokens": 883203.0,
+      "step": 123
+    },
+    {
+      "epoch": 1.8539325842696628,
+      "grad_norm": 2.382763624191284,
+      "learning_rate": 5.41044776119403e-06,
+      "loss": 0.6506,
+      "mean_token_accuracy": 0.8108739107847214,
+      "num_tokens": 891081.0,
+      "step": 124
+    },
+    {
+      "epoch": 1.8689138576779025,
+      "grad_norm": 2.2218973636627197,
+      "learning_rate": 5.37313432835821e-06,
+      "loss": 0.5196,
+      "mean_token_accuracy": 0.8333333134651184,
+      "num_tokens": 899053.0,
+      "step": 125
+    },
+    {
+      "epoch": 1.8838951310861423,
+      "grad_norm": 2.729238748550415,
+      "learning_rate": 5.335820895522389e-06,
+      "loss": 0.6499,
+      "mean_token_accuracy": 0.8122645914554596,
+      "num_tokens": 905078.0,
+      "step": 126
+    },
+    {
+      "epoch": 1.898876404494382,
+      "grad_norm": 2.129035711288452,
+      "learning_rate": 5.298507462686567e-06,
+      "loss": 0.531,
+      "mean_token_accuracy": 0.8345644921064377,
+      "num_tokens": 912716.0,
+      "step": 127
+    },
+    {
+      "epoch": 1.9138576779026217,
+      "grad_norm": 2.543597459793091,
+      "learning_rate": 5.261194029850747e-06,
+      "loss": 0.5738,
+      "mean_token_accuracy": 0.8189967423677444,
+      "num_tokens": 920417.0,
+      "step": 128
+    },
+    {
+      "epoch": 1.9288389513108615,
+      "grad_norm": 2.3534562587738037,
+      "learning_rate": 5.2238805970149255e-06,
+      "loss": 0.5738,
+      "mean_token_accuracy": 0.814308300614357,
+      "num_tokens": 927855.0,
+      "step": 129
+    },
+    {
+      "epoch": 1.9438202247191012,
+      "grad_norm": 2.3981590270996094,
+      "learning_rate": 5.186567164179105e-06,
+      "loss": 0.5595,
+      "mean_token_accuracy": 0.8211537748575211,
+      "num_tokens": 934918.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.9438202247191012,
+      "eval_loss": 1.0272549390792847,
+      "eval_mean_token_accuracy": 0.6856482028961182,
+      "eval_num_tokens": 934918.0,
+      "eval_runtime": 43.4636,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.138,
+      "step": 130
+    },
+    {
+      "epoch": 1.958801498127341,
+      "grad_norm": 2.955871820449829,
+      "learning_rate": 5.149253731343285e-06,
+      "loss": 0.6324,
+      "mean_token_accuracy": 0.8120583146810532,
+      "num_tokens": 941215.0,
+      "step": 131
+    },
+    {
+      "epoch": 1.9737827715355807,
+      "grad_norm": 2.3583202362060547,
+      "learning_rate": 5.111940298507463e-06,
+      "loss": 0.6178,
+      "mean_token_accuracy": 0.811441496014595,
+      "num_tokens": 948780.0,
+      "step": 132
+    },
+    {
+      "epoch": 1.9887640449438202,
+      "grad_norm": 2.0456173419952393,
+      "learning_rate": 5.074626865671642e-06,
+      "loss": 0.5412,
+      "mean_token_accuracy": 0.8333507776260376,
+      "num_tokens": 956929.0,
+      "step": 133
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.892012357711792,
+      "learning_rate": 5.037313432835821e-06,
+      "loss": 0.6559,
+      "mean_token_accuracy": 0.8129192392031351,
+      "num_tokens": 961868.0,
+      "step": 134
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 268,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.886130817743872e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ec0384353a422b288f36ab6c4973742c276c7f6a9e281b414123e60fb46dcf5
+size 6353