Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

chat_template.jinja

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

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44915c2034957f6ec69e01100173113355ea7e3a1bc93be4e585cd0eb985f6a8
+size 4990095032

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6a3dfd127a4d3e947bdc0b85e115f06ce80aeba817045166d8cc6e262d470e
+size 4944309096

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe5d9aa6f93438d32e84460d7aeb1f386892c54a09a3bf88ed32713e6898e36
+size 4996758848

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942461ca68518f562d2dbef921c2b781994f303a6202f2eee728627ed794e9c3
+size 2714579640

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 17645697024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,1957 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "eval_steps": 7,
+  "global_step": 228,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 14.123342514038086,
+      "learning_rate": 0.0,
+      "loss": 2.7783,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 11.786408424377441,
+      "learning_rate": 2.4999999999999998e-06,
+      "loss": 2.2354,
+      "step": 2
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 8.494778633117676,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 2.0283,
+      "step": 3
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 7.215401649475098,
+      "learning_rate": 7.5e-06,
+      "loss": 2.1455,
+      "step": 4
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 8.578252792358398,
+      "learning_rate": 9.999999999999999e-06,
+      "loss": 2.2861,
+      "step": 5
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 4.119718551635742,
+      "learning_rate": 1.25e-05,
+      "loss": 1.7803,
+      "step": 6
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 4.304780006408691,
+      "learning_rate": 1.5e-05,
+      "loss": 1.3184,
+      "step": 7
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 2.8660857677459717,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.248,
+      "step": 8
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 2.7758121490478516,
+      "learning_rate": 1.9999999999999998e-05,
+      "loss": 0.9458,
+      "step": 9
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.466347336769104,
+      "learning_rate": 2.25e-05,
+      "loss": 0.811,
+      "step": 10
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 4.459120273590088,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7944,
+      "step": 11
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.7861258387565613,
+      "learning_rate": 2.75e-05,
+      "loss": 0.7593,
+      "step": 12
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 2.145634412765503,
+      "learning_rate": 3e-05,
+      "loss": 0.6675,
+      "step": 13
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 1.1145251989364624,
+      "learning_rate": 2.9998413478906614e-05,
+      "loss": 0.7485,
+      "step": 14
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.8657529354095459,
+      "learning_rate": 2.9993654251233013e-05,
+      "loss": 0.6072,
+      "step": 15
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.733092725276947,
+      "learning_rate": 2.998572332372787e-05,
+      "loss": 0.6133,
+      "step": 16
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.5715511441230774,
+      "learning_rate": 2.9974622374069024e-05,
+      "loss": 0.6072,
+      "step": 17
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.5022944808006287,
+      "learning_rate": 2.9960353750508586e-05,
+      "loss": 0.5757,
+      "step": 18
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.4509405493736267,
+      "learning_rate": 2.9942920471376185e-05,
+      "loss": 0.5408,
+      "step": 19
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.3787665367126465,
+      "learning_rate": 2.9922326224440496e-05,
+      "loss": 0.5093,
+      "step": 20
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.3237473666667938,
+      "learning_rate": 2.9898575366129145e-05,
+      "loss": 0.4441,
+      "step": 21
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.5597398281097412,
+      "learning_rate": 2.9871672920607158e-05,
+      "loss": 0.4775,
+      "step": 22
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.5664136409759521,
+      "learning_rate": 2.9841624578714165e-05,
+      "loss": 0.4219,
+      "step": 23
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.4183344542980194,
+      "learning_rate": 2.980843669676061e-05,
+      "loss": 0.3811,
+      "step": 24
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.30729541182518005,
+      "learning_rate": 2.977211629518312e-05,
+      "loss": 0.4685,
+      "step": 25
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "eval_loss": 0.41455078125,
+      "eval_runtime": 0.802,
+      "eval_samples_per_second": 9.976,
+      "eval_steps_per_second": 1.247,
+      "step": 25
+    },
+    {
+      "checkpoint_runtime": 31.5266
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.3313934803009033,
+      "learning_rate": 2.973267105705946e-05,
+      "loss": 0.3888,
+      "step": 26
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.25473904609680176,
+      "learning_rate": 2.9690109326483276e-05,
+      "loss": 0.4067,
+      "step": 27
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.27296820282936096,
+      "learning_rate": 2.9644440106799003e-05,
+      "loss": 0.3262,
+      "step": 28
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.29668810963630676,
+      "learning_rate": 2.959567305869736e-05,
+      "loss": 0.3256,
+      "step": 29
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.22976142168045044,
+      "learning_rate": 2.954381849817174e-05,
+      "loss": 0.3541,
+      "step": 30
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.2824176549911499,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 0.2914,
+      "step": 31
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.23928223550319672,
+      "learning_rate": 2.9430891367104196e-05,
+      "loss": 0.326,
+      "step": 32
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.365966796875,
+      "eval_runtime": 0.8155,
+      "eval_samples_per_second": 9.81,
+      "eval_steps_per_second": 1.226,
+      "step": 32
+    },
+    {
+      "checkpoint_runtime": 32.5351
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.18137401342391968,
+      "learning_rate": 2.9369842684732334e-05,
+      "loss": 0.3197,
+      "step": 33
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.21811780333518982,
+      "learning_rate": 2.9305754261223403e-05,
+      "loss": 0.314,
+      "step": 34
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.18523764610290527,
+      "learning_rate": 2.923863965359551e-05,
+      "loss": 0.2606,
+      "step": 35
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.217413529753685,
+      "learning_rate": 2.9168513059014072e-05,
+      "loss": 0.2803,
+      "step": 36
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.15678593516349792,
+      "learning_rate": 2.9095389311788626e-05,
+      "loss": 0.22,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.21294786036014557,
+      "learning_rate": 2.9019283880234828e-05,
+      "loss": 0.3104,
+      "step": 38
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.2676050364971161,
+      "learning_rate": 2.8940212863402334e-05,
+      "loss": 0.2446,
+      "step": 39
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "eval_loss": 0.337890625,
+      "eval_runtime": 0.813,
+      "eval_samples_per_second": 9.841,
+      "eval_steps_per_second": 1.23,
+      "step": 39
+    },
+    {
+      "checkpoint_runtime": 36.0303
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.19905439019203186,
+      "learning_rate": 2.8858192987669303e-05,
+      "loss": 0.2423,
+      "step": 40
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.18775033950805664,
+      "learning_rate": 2.877324160320411e-05,
+      "loss": 0.2909,
+      "step": 41
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.1979457288980484,
+      "learning_rate": 2.8685376680295215e-05,
+      "loss": 0.3044,
+      "step": 42
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.17802807688713074,
+      "learning_rate": 2.8594616805549752e-05,
+      "loss": 0.2039,
+      "step": 43
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.1864515244960785,
+      "learning_rate": 2.8500981177961817e-05,
+      "loss": 0.2296,
+      "step": 44
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.16440877318382263,
+      "learning_rate": 2.8404489604851186e-05,
+      "loss": 0.2193,
+      "step": 45
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.21186216175556183,
+      "learning_rate": 2.8305162497673325e-05,
+      "loss": 0.2739,
+      "step": 46
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "eval_loss": 0.31689453125,
+      "eval_runtime": 0.8123,
+      "eval_samples_per_second": 9.849,
+      "eval_steps_per_second": 1.231,
+      "step": 46
+    },
+    {
+      "checkpoint_runtime": 39.8104
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.16303125023841858,
+      "learning_rate": 2.8203020867701665e-05,
+      "loss": 0.1981,
+      "step": 47
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.16117797791957855,
+      "learning_rate": 2.809808632158294e-05,
+      "loss": 0.2557,
+      "step": 48
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.14011965692043304,
+      "learning_rate": 2.7990381056766583e-05,
+      "loss": 0.2162,
+      "step": 49
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.16410231590270996,
+      "learning_rate": 2.78799278568092e-05,
+      "loss": 0.3088,
+      "step": 50
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.1303449124097824,
+      "learning_rate": 2.7766750086554997e-05,
+      "loss": 0.2766,
+      "step": 51
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.15901443362236023,
+      "learning_rate": 2.7650871687193287e-05,
+      "loss": 0.2126,
+      "step": 52
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.11623891443014145,
+      "learning_rate": 2.753231717119405e-05,
+      "loss": 0.1974,
+      "step": 53
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "eval_loss": 0.30126953125,
+      "eval_runtime": 0.8004,
+      "eval_samples_per_second": 9.995,
+      "eval_steps_per_second": 1.249,
+      "step": 53
+    },
+    {
+      "checkpoint_runtime": 40.2069
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.16020941734313965,
+      "learning_rate": 2.7411111617122658e-05,
+      "loss": 0.2398,
+      "step": 54
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.1458924561738968,
+      "learning_rate": 2.728728066433488e-05,
+      "loss": 0.2607,
+      "step": 55
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.13661666214466095,
+      "learning_rate": 2.7160850507553187e-05,
+      "loss": 0.2785,
+      "step": 56
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.11852806061506271,
+      "learning_rate": 2.7031847891325658e-05,
+      "loss": 0.2462,
+      "step": 57
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.1389610916376114,
+      "learning_rate": 2.6900300104368527e-05,
+      "loss": 0.2575,
+      "step": 58
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.10734441876411438,
+      "learning_rate": 2.6766234973793638e-05,
+      "loss": 0.2186,
+      "step": 59
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.10806363821029663,
+      "learning_rate": 2.6629680859221987e-05,
+      "loss": 0.1858,
+      "step": 60
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.28857421875,
+      "eval_runtime": 0.8012,
+      "eval_samples_per_second": 9.985,
+      "eval_steps_per_second": 1.248,
+      "step": 60
+    },
+    {
+      "checkpoint_runtime": 41.5271
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.11526419222354889,
+      "learning_rate": 2.649066664678467e-05,
+      "loss": 0.1888,
+      "step": 61
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.10889163613319397,
+      "learning_rate": 2.6349221743012394e-05,
+      "loss": 0.1517,
+      "step": 62
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.14918109774589539,
+      "learning_rate": 2.620537606861494e-05,
+      "loss": 0.2682,
+      "step": 63
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.09366485476493835,
+      "learning_rate": 2.605916005215186e-05,
+      "loss": 0.1868,
+      "step": 64
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.12242089211940765,
+      "learning_rate": 2.5910604623595732e-05,
+      "loss": 0.2528,
+      "step": 65
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.12178941071033478,
+      "learning_rate": 2.575974120778934e-05,
+      "loss": 0.1849,
+      "step": 66
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.09551741927862167,
+      "learning_rate": 2.5606601717798212e-05,
+      "loss": 0.1771,
+      "step": 67
+    },
+    {
+      "epoch": 1.763157894736842,
+      "eval_loss": 0.2794189453125,
+      "eval_runtime": 0.8095,
+      "eval_samples_per_second": 9.883,
+      "eval_steps_per_second": 1.235,
+      "step": 67
+    },
+    {
+      "checkpoint_runtime": 44.1795
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.10511334985494614,
+      "learning_rate": 2.5451218548159825e-05,
+      "loss": 0.2087,
+      "step": 68
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.1009010300040245,
+      "learning_rate": 2.5293624568031008e-05,
+      "loss": 0.1678,
+      "step": 69
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.10071597993373871,
+      "learning_rate": 2.5133853114234907e-05,
+      "loss": 0.1874,
+      "step": 70
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.11388185620307922,
+      "learning_rate": 2.4971937984209064e-05,
+      "loss": 0.2075,
+      "step": 71
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.11807021498680115,
+      "learning_rate": 2.4807913428856046e-05,
+      "loss": 0.2014,
+      "step": 72
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.10843336582183838,
+      "learning_rate": 2.464181414529809e-05,
+      "loss": 0.1527,
+      "step": 73
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.12527300417423248,
+      "learning_rate": 2.4473675269537462e-05,
+      "loss": 0.1705,
+      "step": 74
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "eval_loss": 0.272705078125,
+      "eval_runtime": 0.8151,
+      "eval_samples_per_second": 9.815,
+      "eval_steps_per_second": 1.227,
+      "step": 74
+    },
+    {
+      "checkpoint_runtime": 42.1965
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.08646294474601746,
+      "learning_rate": 2.43035323690239e-05,
+      "loss": 0.1304,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.13214462995529175,
+      "learning_rate": 2.413142143513081e-05,
+      "loss": 0.2139,
+      "step": 76
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.10207957029342651,
+      "learning_rate": 2.3957378875541795e-05,
+      "loss": 0.1431,
+      "step": 77
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.1097612977027893,
+      "learning_rate": 2.378144150654911e-05,
+      "loss": 0.1628,
+      "step": 78
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.11010586470365524,
+      "learning_rate": 2.360364654526569e-05,
+      "loss": 0.2029,
+      "step": 79
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.1569771021604538,
+      "learning_rate": 2.3424031601752395e-05,
+      "loss": 0.2233,
+      "step": 80
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.08403217047452927,
+      "learning_rate": 2.324263467106209e-05,
+      "loss": 0.1263,
+      "step": 81
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "eval_loss": 0.2679443359375,
+      "eval_runtime": 0.8065,
+      "eval_samples_per_second": 9.92,
+      "eval_steps_per_second": 1.24,
+      "step": 81
+    },
+    {
+      "checkpoint_runtime": 42.0356
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.12342365831136703,
+      "learning_rate": 2.305949412520236e-05,
+      "loss": 0.1505,
+      "step": 82
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.09468170255422592,
+      "learning_rate": 2.28746487050184e-05,
+      "loss": 0.1499,
+      "step": 83
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.11681695282459259,
+      "learning_rate": 2.2688137511997978e-05,
+      "loss": 0.2051,
+      "step": 84
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.09306800365447998,
+      "learning_rate": 2.25e-05,
+      "loss": 0.1341,
+      "step": 85
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.12549293041229248,
+      "learning_rate": 2.2310275966908635e-05,
+      "loss": 0.194,
+      "step": 86
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.0926017239689827,
+      "learning_rate": 2.2119005546214607e-05,
+      "loss": 0.1586,
+      "step": 87
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.13283279538154602,
+      "learning_rate": 2.192622919852551e-05,
+      "loss": 0.2432,
+      "step": 88
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "eval_loss": 0.2635498046875,
+      "eval_runtime": 0.7974,
+      "eval_samples_per_second": 10.032,
+      "eval_steps_per_second": 1.254,
+      "step": 88
+    },
+    {
+      "checkpoint_runtime": 36.4415
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.1036519706249237,
+      "learning_rate": 2.1731987703006933e-05,
+      "loss": 0.2121,
+      "step": 89
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.10677948594093323,
+      "learning_rate": 2.153632214875619e-05,
+      "loss": 0.1557,
+      "step": 90
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.11184219270944595,
+      "learning_rate": 2.1339273926110493e-05,
+      "loss": 0.1479,
+      "step": 91
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.11406749486923218,
+      "learning_rate": 2.114088471789139e-05,
+      "loss": 0.1845,
+      "step": 92
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.11213068664073944,
+      "learning_rate": 2.0941196490587352e-05,
+      "loss": 0.2025,
+      "step": 93
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.1360907405614853,
+      "learning_rate": 2.074025148547635e-05,
+      "loss": 0.2238,
+      "step": 94
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.11547745764255524,
+      "learning_rate": 2.0538092209690267e-05,
+      "loss": 0.1953,
+      "step": 95
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.2596435546875,
+      "eval_runtime": 0.8046,
+      "eval_samples_per_second": 9.943,
+      "eval_steps_per_second": 1.243,
+      "step": 95
+    },
+    {
+      "checkpoint_runtime": 40.3059
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.11219988018274307,
+      "learning_rate": 2.033476142722315e-05,
+      "loss": 0.2059,
+      "step": 96
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.10362070798873901,
+      "learning_rate": 2.0130302149885033e-05,
+      "loss": 0.1729,
+      "step": 97
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.0941133201122284,
+      "learning_rate": 1.9924757628203417e-05,
+      "loss": 0.1473,
+      "step": 98
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.10246875882148743,
+      "learning_rate": 1.9718171342274207e-05,
+      "loss": 0.15,
+      "step": 99
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.08190064132213593,
+      "learning_rate": 1.9510586992564095e-05,
+      "loss": 0.1168,
+      "step": 100
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.136471688747406,
+      "learning_rate": 1.9302048490666356e-05,
+      "loss": 0.2189,
+      "step": 101
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.08835738897323608,
+      "learning_rate": 1.9092599950011918e-05,
+      "loss": 0.149,
+      "step": 102
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "eval_loss": 0.2567138671875,
+      "eval_runtime": 0.8013,
+      "eval_samples_per_second": 9.984,
+      "eval_steps_per_second": 1.248,
+      "step": 102
+    },
+    {
+      "checkpoint_runtime": 38.556
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.11610888689756393,
+      "learning_rate": 1.888228567653781e-05,
+      "loss": 0.2081,
+      "step": 103
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.10228007286787033,
+      "learning_rate": 1.8671150159314858e-05,
+      "loss": 0.1489,
+      "step": 104
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.0931699350476265,
+      "learning_rate": 1.8459238061136604e-05,
+      "loss": 0.1448,
+      "step": 105
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.10062670707702637,
+      "learning_rate": 1.8246594209071543e-05,
+      "loss": 0.1709,
+      "step": 106
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.09129922837018967,
+      "learning_rate": 1.8033263584980572e-05,
+      "loss": 0.1361,
+      "step": 107
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.10449088364839554,
+      "learning_rate": 1.7819291316001676e-05,
+      "loss": 0.1535,
+      "step": 108
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.09913967549800873,
+      "learning_rate": 1.760472266500396e-05,
+      "loss": 0.1729,
+      "step": 109
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "eval_loss": 0.2550048828125,
+      "eval_runtime": 0.8124,
+      "eval_samples_per_second": 9.848,
+      "eval_steps_per_second": 1.231,
+      "step": 109
+    },
+    {
+      "checkpoint_runtime": 37.8128
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.10686536133289337,
+      "learning_rate": 1.738960302101284e-05,
+      "loss": 0.1677,
+      "step": 110
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.08579204231500626,
+      "learning_rate": 1.7173977889608698e-05,
+      "loss": 0.1252,
+      "step": 111
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.10212811082601547,
+      "learning_rate": 1.6957892883300778e-05,
+      "loss": 0.1406,
+      "step": 112
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.08335171639919281,
+      "learning_rate": 1.6741393711878455e-05,
+      "loss": 0.1065,
+      "step": 113
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.1307053118944168,
+      "learning_rate": 1.652452617274203e-05,
+      "loss": 0.1786,
+      "step": 114
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.09419464319944382,
+      "learning_rate": 1.6307336141214877e-05,
+      "loss": 0.1166,
+      "step": 115
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.11391319334506989,
+      "learning_rate": 1.608986956083916e-05,
+      "loss": 0.1374,
+      "step": 116
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "eval_loss": 0.25390625,
+      "eval_runtime": 0.808,
+      "eval_samples_per_second": 9.901,
+      "eval_steps_per_second": 1.238,
+      "step": 116
+    },
+    {
+      "checkpoint_runtime": 35.3283
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.12956199049949646,
+      "learning_rate": 1.587217243365714e-05,
+      "loss": 0.1718,
+      "step": 117
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.11613801121711731,
+      "learning_rate": 1.5654290810480043e-05,
+      "loss": 0.1885,
+      "step": 118
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.11859948188066483,
+      "learning_rate": 1.543627078114667e-05,
+      "loss": 0.1041,
+      "step": 119
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.12278915196657181,
+      "learning_rate": 1.5218158464773742e-05,
+      "loss": 0.1266,
+      "step": 120
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.09654603898525238,
+      "learning_rate": 1.5e-05,
+      "loss": 0.1268,
+      "step": 121
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.11280681937932968,
+      "learning_rate": 1.478184153522626e-05,
+      "loss": 0.1761,
+      "step": 122
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.09958962351083755,
+      "learning_rate": 1.4563729218853329e-05,
+      "loss": 0.1131,
+      "step": 123
+    },
+    {
+      "epoch": 3.236842105263158,
+      "eval_loss": 0.251953125,
+      "eval_runtime": 0.8043,
+      "eval_samples_per_second": 9.947,
+      "eval_steps_per_second": 1.243,
+      "step": 123
+    },
+    {
+      "checkpoint_runtime": 38.2324
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.10516051948070526,
+      "learning_rate": 1.4345709189519963e-05,
+      "loss": 0.1671,
+      "step": 124
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.09277815371751785,
+      "learning_rate": 1.4127827566342864e-05,
+      "loss": 0.1356,
+      "step": 125
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.15271221101284027,
+      "learning_rate": 1.3910130439160841e-05,
+      "loss": 0.2115,
+      "step": 126
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.11493046581745148,
+      "learning_rate": 1.3692663858785127e-05,
+      "loss": 0.1829,
+      "step": 127
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.09166600555181503,
+      "learning_rate": 1.3475473827257972e-05,
+      "loss": 0.134,
+      "step": 128
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.08230035752058029,
+      "learning_rate": 1.3258606288121545e-05,
+      "loss": 0.1275,
+      "step": 129
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.1134151816368103,
+      "learning_rate": 1.304210711669923e-05,
+      "loss": 0.1599,
+      "step": 130
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.7944,
+      "eval_samples_per_second": 10.07,
+      "eval_steps_per_second": 1.259,
+      "step": 130
+    },
+    {
+      "checkpoint_runtime": 38.2938
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.11686340719461441,
+      "learning_rate": 1.2826022110391301e-05,
+      "loss": 0.1762,
+      "step": 131
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.11043721437454224,
+      "learning_rate": 1.2610396978987163e-05,
+      "loss": 0.1951,
+      "step": 132
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.09822215884923935,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.1701,
+      "step": 133
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.11570524424314499,
+      "learning_rate": 1.2180708683998323e-05,
+      "loss": 0.1807,
+      "step": 134
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.09753210097551346,
+      "learning_rate": 1.1966736415019434e-05,
+      "loss": 0.1514,
+      "step": 135
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.08166804909706116,
+      "learning_rate": 1.1753405790928458e-05,
+      "loss": 0.1289,
+      "step": 136
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.10317232459783554,
+      "learning_rate": 1.1540761938863397e-05,
+      "loss": 0.1317,
+      "step": 137
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.8061,
+      "eval_samples_per_second": 9.924,
+      "eval_steps_per_second": 1.241,
+      "step": 137
+    },
+    {
+      "checkpoint_runtime": 37.5123
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.07060441374778748,
+      "learning_rate": 1.1328849840685143e-05,
+      "loss": 0.1013,
+      "step": 138
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.11906401067972183,
+      "learning_rate": 1.1117714323462188e-05,
+      "loss": 0.1916,
+      "step": 139
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.08510293066501617,
+      "learning_rate": 1.090740004998809e-05,
+      "loss": 0.1299,
+      "step": 140
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.11465775966644287,
+      "learning_rate": 1.069795150933365e-05,
+      "loss": 0.1832,
+      "step": 141
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.08759936690330505,
+      "learning_rate": 1.0489413007435905e-05,
+      "loss": 0.1298,
+      "step": 142
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.08069173991680145,
+      "learning_rate": 1.0281828657725798e-05,
+      "loss": 0.1274,
+      "step": 143
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.10825315862894058,
+      "learning_rate": 1.0075242371796586e-05,
+      "loss": 0.1506,
+      "step": 144
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "eval_loss": 0.2496337890625,
+      "eval_runtime": 0.812,
+      "eval_samples_per_second": 9.852,
+      "eval_steps_per_second": 1.231,
+      "step": 144
+    },
+    {
+      "checkpoint_runtime": 31.4923
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.08054646104574203,
+      "learning_rate": 9.86969785011497e-06,
+      "loss": 0.1196,
+      "step": 145
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.09322228282690048,
+      "learning_rate": 9.665238572776856e-06,
+      "loss": 0.135,
+      "step": 146
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.0945623368024826,
+      "learning_rate": 9.461907790309735e-06,
+      "loss": 0.1529,
+      "step": 147
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.09744946658611298,
+      "learning_rate": 9.259748514523654e-06,
+      "loss": 0.1484,
+      "step": 148
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.08375933021306992,
+      "learning_rate": 9.058803509412647e-06,
+      "loss": 0.1099,
+      "step": 149
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.09268806129693985,
+      "learning_rate": 8.859115282108611e-06,
+      "loss": 0.1236,
+      "step": 150
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.07510408014059067,
+      "learning_rate": 8.66072607388951e-06,
+      "loss": 0.0944,
+      "step": 151
+    },
+    {
+      "epoch": 3.973684210526316,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.8011,
+      "eval_samples_per_second": 9.987,
+      "eval_steps_per_second": 1.248,
+      "step": 151
+    },
+    {
+      "checkpoint_runtime": 35.0463
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12267880141735077,
+      "learning_rate": 8.463677851243813e-06,
+      "loss": 0.1575,
+      "step": 152
+    },
+    {
+      "epoch": 4.026315789473684,
+      "grad_norm": 0.08687010407447815,
+      "learning_rate": 8.268012296993067e-06,
+      "loss": 0.1018,
+      "step": 153
+    },
+    {
+      "epoch": 4.052631578947368,
+      "grad_norm": 0.08043317496776581,
+      "learning_rate": 8.073770801474494e-06,
+      "loss": 0.1215,
+      "step": 154
+    },
+    {
+      "epoch": 4.078947368421052,
+      "grad_norm": 0.10377892851829529,
+      "learning_rate": 7.880994453785394e-06,
+      "loss": 0.1522,
+      "step": 155
+    },
+    {
+      "epoch": 4.105263157894737,
+      "grad_norm": 0.12225374579429626,
+      "learning_rate": 7.689724033091366e-06,
+      "loss": 0.168,
+      "step": 156
+    },
+    {
+      "epoch": 4.131578947368421,
+      "grad_norm": 0.07841687649488449,
+      "learning_rate": 7.500000000000004e-06,
+      "loss": 0.0917,
+      "step": 157
+    },
+    {
+      "epoch": 4.157894736842105,
+      "grad_norm": 0.0922280102968216,
+      "learning_rate": 7.311862488002022e-06,
+      "loss": 0.1127,
+      "step": 158
+    },
+    {
+      "epoch": 4.157894736842105,
+      "eval_loss": 0.249755859375,
+      "eval_runtime": 0.7936,
+      "eval_samples_per_second": 10.081,
+      "eval_steps_per_second": 1.26,
+      "step": 158
+    },
+    {
+      "checkpoint_runtime": 31.4728
+    },
+    {
+      "epoch": 4.184210526315789,
+      "grad_norm": 0.08898007124662399,
+      "learning_rate": 7.1253512949815995e-06,
+      "loss": 0.113,
+      "step": 159
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.11133883148431778,
+      "learning_rate": 6.9405058747976406e-06,
+      "loss": 0.1578,
+      "step": 160
+    },
+    {
+      "epoch": 4.2368421052631575,
+      "grad_norm": 0.07919172942638397,
+      "learning_rate": 6.75736532893791e-06,
+      "loss": 0.1006,
+      "step": 161
+    },
+    {
+      "epoch": 4.2631578947368425,
+      "grad_norm": 0.10553218424320221,
+      "learning_rate": 6.575968398247609e-06,
+      "loss": 0.1496,
+      "step": 162
+    },
+    {
+      "epoch": 4.2894736842105265,
+      "grad_norm": 0.10168725997209549,
+      "learning_rate": 6.3963534547343126e-06,
+      "loss": 0.121,
+      "step": 163
+    },
+    {
+      "epoch": 4.315789473684211,
+      "grad_norm": 0.10766523331403732,
+      "learning_rate": 6.218558493450893e-06,
+      "loss": 0.1906,
+      "step": 164
+    },
+    {
+      "epoch": 4.342105263157895,
+      "grad_norm": 0.11475641280412674,
+      "learning_rate": 6.0426211244582105e-06,
+      "loss": 0.1643,
+      "step": 165
+    },
+    {
+      "epoch": 4.342105263157895,
+      "eval_loss": 0.24951171875,
+      "eval_runtime": 0.813,
+      "eval_samples_per_second": 9.84,
+      "eval_steps_per_second": 1.23,
+      "step": 165
+    },
+    {
+      "checkpoint_runtime": 33.031
+    },
+    {
+      "epoch": 4.368421052631579,
+      "grad_norm": 0.09534571319818497,
+      "learning_rate": 5.86857856486919e-06,
+      "loss": 0.1204,
+      "step": 166
+    },
+    {
+      "epoch": 4.394736842105263,
+      "grad_norm": 0.08268483728170395,
+      "learning_rate": 5.696467630976101e-06,
+      "loss": 0.1153,
+      "step": 167
+    },
+    {
+      "epoch": 4.421052631578947,
+      "grad_norm": 0.10098259150981903,
+      "learning_rate": 5.526324730462539e-06,
+      "loss": 0.144,
+      "step": 168
+    },
+    {
+      "epoch": 4.447368421052632,
+      "grad_norm": 0.11118590086698532,
+      "learning_rate": 5.3581858547019095e-06,
+      "loss": 0.1598,
+      "step": 169
+    },
+    {
+      "epoch": 4.473684210526316,
+      "grad_norm": 0.10616252571344376,
+      "learning_rate": 5.192086571143956e-06,
+      "loss": 0.1776,
+      "step": 170
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.1017308160662651,
+      "learning_rate": 5.0280620157909316e-06,
+      "loss": 0.154,
+      "step": 171
+    },
+    {
+      "epoch": 4.526315789473684,
+      "grad_norm": 0.11745047569274902,
+      "learning_rate": 4.8661468857650965e-06,
+      "loss": 0.1636,
+      "step": 172
+    },
+    {
+      "epoch": 4.526315789473684,
+      "eval_loss": 0.2484130859375,
+      "eval_runtime": 0.7907,
+      "eval_samples_per_second": 10.118,
+      "eval_steps_per_second": 1.265,
+      "step": 172
+    },
+    {
+      "checkpoint_runtime": 33.7914
+    },
+    {
+      "epoch": 4.552631578947368,
+      "grad_norm": 0.09687429666519165,
+      "learning_rate": 4.706375431968998e-06,
+      "loss": 0.1372,
+      "step": 173
+    },
+    {
+      "epoch": 4.578947368421053,
+      "grad_norm": 0.08014977723360062,
+      "learning_rate": 4.54878145184018e-06,
+      "loss": 0.1173,
+      "step": 174
+    },
+    {
+      "epoch": 4.605263157894737,
+      "grad_norm": 0.08149994909763336,
+      "learning_rate": 4.393398282201788e-06,
+      "loss": 0.1195,
+      "step": 175
+    },
+    {
+      "epoch": 4.631578947368421,
+      "grad_norm": 0.07206987589597702,
+      "learning_rate": 4.240258792210657e-06,
+      "loss": 0.0919,
+      "step": 176
+    },
+    {
+      "epoch": 4.657894736842105,
+      "grad_norm": 0.11085452884435654,
+      "learning_rate": 4.089395376404269e-06,
+      "loss": 0.1746,
+      "step": 177
+    },
+    {
+      "epoch": 4.684210526315789,
+      "grad_norm": 0.08134956657886505,
+      "learning_rate": 3.940839947848141e-06,
+      "loss": 0.1178,
+      "step": 178
+    },
+    {
+      "epoch": 4.7105263157894735,
+      "grad_norm": 0.10688931494951248,
+      "learning_rate": 3.7946239313850626e-06,
+      "loss": 0.1667,
+      "step": 179
+    },
+    {
+      "epoch": 4.7105263157894735,
+      "eval_loss": 0.249267578125,
+      "eval_runtime": 0.8044,
+      "eval_samples_per_second": 9.946,
+      "eval_steps_per_second": 1.243,
+      "step": 179
+    },
+    {
+      "checkpoint_runtime": 31.3845
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.08253388851881027,
+      "learning_rate": 3.6507782569876075e-06,
+      "loss": 0.1181,
+      "step": 180
+    },
+    {
+      "epoch": 4.7631578947368425,
+      "grad_norm": 0.08573804795742035,
+      "learning_rate": 3.5093333532153316e-06,
+      "loss": 0.1164,
+      "step": 181
+    },
+    {
+      "epoch": 4.7894736842105265,
+      "grad_norm": 0.09091360867023468,
+      "learning_rate": 3.3703191407780113e-06,
+      "loss": 0.1367,
+      "step": 182
+    },
+    {
+      "epoch": 4.815789473684211,
+      "grad_norm": 0.0778035819530487,
+      "learning_rate": 3.2337650262063646e-06,
+      "loss": 0.1093,
+      "step": 183
+    },
+    {
+      "epoch": 4.842105263157895,
+      "grad_norm": 0.09607183933258057,
+      "learning_rate": 3.0996998956314744e-06,
+      "loss": 0.1236,
+      "step": 184
+    },
+    {
+      "epoch": 4.868421052631579,
+      "grad_norm": 0.10202693939208984,
+      "learning_rate": 2.9681521086743426e-06,
+      "loss": 0.1406,
+      "step": 185
+    },
+    {
+      "epoch": 4.894736842105263,
+      "grad_norm": 0.09527413547039032,
+      "learning_rate": 2.839149492446817e-06,
+      "loss": 0.1365,
+      "step": 186
+    },
+    {
+      "epoch": 4.894736842105263,
+      "eval_loss": 0.2496337890625,
+      "eval_runtime": 0.8061,
+      "eval_samples_per_second": 9.925,
+      "eval_steps_per_second": 1.241,
+      "step": 186
+    },
+    {
+      "checkpoint_runtime": 31.2214
+    },
+    {
+      "epoch": 4.921052631578947,
+      "grad_norm": 0.07628463953733444,
+      "learning_rate": 2.7127193356651214e-06,
+      "loss": 0.1004,
+      "step": 187
+    },
+    {
+      "epoch": 4.947368421052632,
+      "grad_norm": 0.08375431597232819,
+      "learning_rate": 2.588888382877342e-06,
+      "loss": 0.1135,
+      "step": 188
+    },
+    {
+      "epoch": 4.973684210526316,
+      "grad_norm": 0.06959506869316101,
+      "learning_rate": 2.467682828805956e-06,
+      "loss": 0.0866,
+      "step": 189
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.09036092460155487,
+      "learning_rate": 2.3491283128067174e-06,
+      "loss": 0.1436,
+      "step": 190
+    },
+    {
+      "epoch": 5.026315789473684,
+      "grad_norm": 0.06946128606796265,
+      "learning_rate": 2.233249913445004e-06,
+      "loss": 0.0924,
+      "step": 191
+    },
+    {
+      "epoch": 5.052631578947368,
+      "grad_norm": 0.07662049680948257,
+      "learning_rate": 2.120072143190806e-06,
+      "loss": 0.1122,
+      "step": 192
+    },
+    {
+      "epoch": 5.078947368421052,
+      "grad_norm": 0.09436455368995667,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.1403,
+      "step": 193
+    },
+    {
+      "epoch": 5.078947368421052,
+      "eval_loss": 0.2510986328125,
+      "eval_runtime": 0.8015,
+      "eval_samples_per_second": 9.981,
+      "eval_steps_per_second": 1.248,
+      "step": 193
+    },
+    {
+      "checkpoint_runtime": 31.5349
+    },
+    {
+      "epoch": 5.105263157894737,
+      "grad_norm": 0.113802470266819,
+      "learning_rate": 1.9019136784170638e-06,
+      "loss": 0.1549,
+      "step": 194
+    },
+    {
+      "epoch": 5.131578947368421,
+      "grad_norm": 0.07214430719614029,
+      "learning_rate": 1.7969791322983354e-06,
+      "loss": 0.0841,
+      "step": 195
+    },
+    {
+      "epoch": 5.157894736842105,
+      "grad_norm": 0.08027806133031845,
+      "learning_rate": 1.6948375023266743e-06,
+      "loss": 0.1038,
+      "step": 196
+    },
+    {
+      "epoch": 5.184210526315789,
+      "grad_norm": 0.07316026836633682,
+      "learning_rate": 1.5955103951488177e-06,
+      "loss": 0.1045,
+      "step": 197
+    },
+    {
+      "epoch": 5.2105263157894735,
+      "grad_norm": 0.09602973610162735,
+      "learning_rate": 1.4990188220381828e-06,
+      "loss": 0.1469,
+      "step": 198
+    },
+    {
+      "epoch": 5.2368421052631575,
+      "grad_norm": 0.07372312247753143,
+      "learning_rate": 1.4053831944502509e-06,
+      "loss": 0.0934,
+      "step": 199
+    },
+    {
+      "epoch": 5.2631578947368425,
+      "grad_norm": 0.0949590802192688,
+      "learning_rate": 1.3146233197047897e-06,
+      "loss": 0.14,
+      "step": 200
+    },
+    {
+      "epoch": 5.2631578947368425,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.7977,
+      "eval_samples_per_second": 10.029,
+      "eval_steps_per_second": 1.254,
+      "step": 200
+    },
+    {
+      "checkpoint_runtime": 31.5303
+    },
+    {
+      "epoch": 5.2894736842105265,
+      "grad_norm": 0.08007413893938065,
+      "learning_rate": 1.2267583967958918e-06,
+      "loss": 0.1125,
+      "step": 201
+    },
+    {
+      "epoch": 5.315789473684211,
+      "grad_norm": 0.09657692164182663,
+      "learning_rate": 1.1418070123306989e-06,
+      "loss": 0.1786,
+      "step": 202
+    },
+    {
+      "epoch": 5.342105263157895,
+      "grad_norm": 0.09067568928003311,
+      "learning_rate": 1.059787136597662e-06,
+      "loss": 0.1538,
+      "step": 203
+    },
+    {
+      "epoch": 5.368421052631579,
+      "grad_norm": 0.07631859183311462,
+      "learning_rate": 9.807161197651743e-07,
+      "loss": 0.113,
+      "step": 204
+    },
+    {
+      "epoch": 5.394736842105263,
+      "grad_norm": 0.07498761266469955,
+      "learning_rate": 9.046106882113753e-07,
+      "loss": 0.1086,
+      "step": 205
+    },
+    {
+      "epoch": 5.421052631578947,
+      "grad_norm": 0.08239156007766724,
+      "learning_rate": 8.314869409859299e-07,
+      "loss": 0.1353,
+      "step": 206
+    },
+    {
+      "epoch": 5.447368421052632,
+      "grad_norm": 0.09166432917118073,
+      "learning_rate": 7.613603464044916e-07,
+      "loss": 0.1503,
+      "step": 207
+    },
+    {
+      "epoch": 5.447368421052632,
+      "eval_loss": 0.249755859375,
+      "eval_runtime": 0.8096,
+      "eval_samples_per_second": 9.881,
+      "eval_steps_per_second": 1.235,
+      "step": 207
+    },
+    {
+      "checkpoint_runtime": 33.3655
+    },
+    {
+      "epoch": 5.473684210526316,
+      "grad_norm": 0.09114815294742584,
+      "learning_rate": 6.942457387765977e-07,
+      "loss": 0.1682,
+      "step": 208
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.0852048397064209,
+      "learning_rate": 6.301573152676665e-07,
+      "loss": 0.1456,
+      "step": 209
+    },
+    {
+      "epoch": 5.526315789473684,
+      "grad_norm": 0.08879265934228897,
+      "learning_rate": 5.691086328958028e-07,
+      "loss": 0.1549,
+      "step": 210
+    },
+    {
+      "epoch": 5.552631578947368,
+      "grad_norm": 0.08327372372150421,
+      "learning_rate": 5.11112605663977e-07,
+      "loss": 0.1296,
+      "step": 211
+    },
+    {
+      "epoch": 5.578947368421053,
+      "grad_norm": 0.07043126225471497,
+      "learning_rate": 4.5618150182826004e-07,
+      "loss": 0.1112,
+      "step": 212
+    },
+    {
+      "epoch": 5.605263157894737,
+      "grad_norm": 0.07754973322153091,
+      "learning_rate": 4.043269413026429e-07,
+      "loss": 0.1138,
+      "step": 213
+    },
+    {
+      "epoch": 5.631578947368421,
+      "grad_norm": 0.06299207359552383,
+      "learning_rate": 3.5555989320099957e-07,
+      "loss": 0.0872,
+      "step": 214
+    },
+    {
+      "epoch": 5.631578947368421,
+      "eval_loss": 0.249755859375,
+      "eval_runtime": 0.8001,
+      "eval_samples_per_second": 9.999,
+      "eval_steps_per_second": 1.25,
+      "step": 214
+    },
+    {
+      "checkpoint_runtime": 30.9131
+    },
+    {
+      "epoch": 5.657894736842105,
+      "grad_norm": 0.0914757251739502,
+      "learning_rate": 3.0989067351672783e-07,
+      "loss": 0.1658,
+      "step": 215
+    },
+    {
+      "epoch": 5.684210526315789,
+      "grad_norm": 0.07366300374269485,
+      "learning_rate": 2.673289429405401e-07,
+      "loss": 0.1121,
+      "step": 216
+    },
+    {
+      "epoch": 5.7105263157894735,
+      "grad_norm": 0.08791062235832214,
+      "learning_rate": 2.278837048168797e-07,
+      "loss": 0.1595,
+      "step": 217
+    },
+    {
+      "epoch": 5.7368421052631575,
+      "grad_norm": 0.07090424746274948,
+      "learning_rate": 1.9156330323938932e-07,
+      "loss": 0.1126,
+      "step": 218
+    },
+    {
+      "epoch": 5.7631578947368425,
+      "grad_norm": 0.0748855322599411,
+      "learning_rate": 1.5837542128583294e-07,
+      "loss": 0.1116,
+      "step": 219
+    },
+    {
+      "epoch": 5.7894736842105265,
+      "grad_norm": 0.08152199536561966,
+      "learning_rate": 1.2832707939284428e-07,
+      "loss": 0.1309,
+      "step": 220
+    },
+    {
+      "epoch": 5.815789473684211,
+      "grad_norm": 0.07014008611440659,
+      "learning_rate": 1.0142463387085465e-07,
+      "loss": 0.105,
+      "step": 221
+    },
+    {
+      "epoch": 5.815789473684211,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.8026,
+      "eval_samples_per_second": 9.968,
+      "eval_steps_per_second": 1.246,
+      "step": 221
+    },
+    {
+      "checkpoint_runtime": 30.8188
+    },
+    {
+      "epoch": 5.842105263157895,
+      "grad_norm": 0.07225294411182404,
+      "learning_rate": 7.767377555950527e-08,
+      "loss": 0.1183,
+      "step": 222
+    },
+    {
+      "epoch": 5.868421052631579,
+      "grad_norm": 0.07823792099952698,
+      "learning_rate": 5.7079528623816824e-08,
+      "loss": 0.1349,
+      "step": 223
+    },
+    {
+      "epoch": 5.894736842105263,
+      "grad_norm": 0.08648072183132172,
+      "learning_rate": 3.964624949141626e-08,
+      "loss": 0.1313,
+      "step": 224
+    },
+    {
+      "epoch": 5.921052631578947,
+      "grad_norm": 0.06885388493537903,
+      "learning_rate": 2.5377625930977367e-08,
+      "loss": 0.0965,
+      "step": 225
+    },
+    {
+      "epoch": 5.947368421052632,
+      "grad_norm": 0.07451262325048447,
+      "learning_rate": 1.4276676272133027e-08,
+      "loss": 0.1091,
+      "step": 226
+    },
+    {
+      "epoch": 5.973684210526316,
+      "grad_norm": 0.06409759074449539,
+      "learning_rate": 6.345748766991011e-09,
+      "loss": 0.0834,
+      "step": 227
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.08607470989227295,
+      "learning_rate": 1.5865210933879714e-09,
+      "loss": 0.1385,
+      "step": 228
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.2498779296875,
+      "eval_runtime": 0.8072,
+      "eval_samples_per_second": 9.911,
+      "eval_steps_per_second": 1.239,
+      "step": 228
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 7,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2552843457614316e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}