Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+base_model: Qwen/Qwen3-8B
+library_name: peft
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -1,18 +1,11 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
-  "auto_mapping": {
-    "base_model_class": "GptOssForCausalLM",
-    "parent_library": "transformers.models.gpt_oss.modeling_gpt_oss",
-    "unsloth_fixed": true
-  },
-  "base_model_name_or_path": "unsloth/gpt-oss-20b-unsloth-bnb-4bit",
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-8B",
   "bias": "none",
   "corda_config": null,
-  "ensure_weight_tying": false,
   "eva_config": null,
-  "exclude_modules": null,
+  "exclude_modules": [],
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -20,34 +13,27 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 128,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.1",
-  "qalora_group_size": 16,
-  "r": 8,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "o_proj",
-    "q_proj",
-    "gate_proj",
     "k_proj",
+    "q_proj",
     "down_proj",
     "up_proj",
-    "v_proj"
-  ],
-  "target_parameters": [
-    "mlp.experts.gate_up_proj",
-    "mlp.experts.down_proj"
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,
-  "use_qalora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f79a850448053f4331e722e4cf61ea6529db550128b8be6cc929a9aed03caea
-size 15950616
+oid sha256:682f1d9b3a95bb64eae77e1436e29c2888a579a24892afe0c26c69f7a7d3262a
+size 698419728

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

@@ -1,315 +1,89 @@
-{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
-{#-
-  In addition to the normal inputs of `messages` and `tools`, this template also accepts the
-  following kwargs:
-  - "builtin_tools": A list, can contain "browser" and/or "python".
-  - "model_identity": A string that optionally describes the model identity.
-  - "reasoning_effort": A string that describes the reasoning effort, defaults to "medium".
- #}
-
-{#- Tool Definition Rendering ============================================== #}
-{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
-    {%- if param_spec.type == "array" -%}
-        {%- if param_spec['items'] -%}
-            {%- if param_spec['items']['type'] == "string" -%}
-                {{- "string[]" }}
-            {%- elif param_spec['items']['type'] == "number" -%}
-                {{- "number[]" }}
-            {%- elif param_spec['items']['type'] == "integer" -%}
-                {{- "number[]" }}
-            {%- elif param_spec['items']['type'] == "boolean" -%}
-                {{- "boolean[]" }}
-            {%- else -%}
-                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
-                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
-                    {{- "any[]" }}
-                {%- else -%}
-                    {{- inner_type + "[]" }}
-                {%- endif -%}
-            {%- endif -%}
-            {%- if param_spec.nullable -%}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- else -%}
-            {{- "any[]" }}
-            {%- if param_spec.nullable -%}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- endif -%}
-    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
-        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
-        {%- if param_spec.type | length > 1 -%}
-            {{- param_spec.type | join(" | ") }}
-        {%- else -%}
-            {{- param_spec.type[0] }}
-        {%- endif -%}
-    {%- elif param_spec.oneOf -%}
-        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
-        {%- set has_object_variants = false -%}
-        {%- for variant in param_spec.oneOf -%}
-            {%- if variant.type == "object" -%}
-                {%- set has_object_variants = true -%}
-            {%- endif -%}
-        {%- endfor -%}
-        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
-            {{- "any" }}
-        {%- else -%}
-            {%- for variant in param_spec.oneOf -%}
-                {{- render_typescript_type(variant, required_params) -}}
-                {%- if variant.description %}
-                    {{- "// " + variant.description }}
-                {%- endif -%}
-                {%- if variant.default is defined %}
-                    {{ "// default: " + variant.default|tojson }}
-                {%- endif -%}
-                {%- if not loop.last %}
-                    {{- " | " }}
-                {% endif -%}
-            {%- endfor -%}
-        {%- endif -%}
-    {%- elif param_spec.type == "string" -%}
-        {%- if param_spec.enum -%}
-            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
-        {%- else -%}
-            {{- "string" }}
-            {%- if param_spec.nullable %}
-                {{- " | null" }}
-            {%- endif -%}
-        {%- endif -%}
-    {%- elif param_spec.type == "number" -%}
-        {{- "number" }}
-    {%- elif param_spec.type == "integer" -%}
-        {{- "number" }}
-    {%- elif param_spec.type == "boolean" -%}
-        {{- "boolean" }}
-
-    {%- elif param_spec.type == "object" -%}
-        {%- if param_spec.properties -%}
-            {{- "{\n" }}
-            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
-                {{- prop_name -}}
-                {%- if prop_name not in (param_spec.required or []) -%}
-                    {{- "?" }}
-                {%- endif -%}
-                {{- ": " }}
-                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
-                {%- if not loop.last -%}
-                    {{-", " }}
-                {%- endif -%}
-            {%- endfor -%}
-            {{- "}" }}
-        {%- else -%}
-            {{- "object" }}
-        {%- endif -%}
-    {%- else -%}
-        {{- "any" }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{%- macro render_tool_namespace(namespace_name, tools) -%}
-    {{- "## " + namespace_name + "\n\n" }}
-    {{- "namespace " + namespace_name + " {\n\n" }}
+{%- 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 %}
-        {%- set tool = tool.function %}
-        {{- "// " + tool.description + "\n" }}
-        {{- "type "+ tool.name + " = " }}
-        {%- if tool.parameters and tool.parameters.properties -%}
-            {{- "(_: " }}
-            {{- "{\n" }}
-            {%- for param_name, param_spec in tool.parameters.properties.items() %}
-                {{- "// " + param_spec.description + "\n" }}
-                {{- param_name }}
-                {%- if param_name not in (tool.parameters.required or []) -%}
-                    {{- "?" }}
-                {%- endif -%}
-                {{- ": " }}
-                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
-                {%- if param_spec.default is defined -%}
-                    {%- if param_spec.enum %}
-                        {{- ", // default: " + param_spec.default }}
-                    {%- elif param_spec.oneOf %}
-                        {{- "// default: " + param_spec.default }}
-                    {%- else %}
-                        {{- ", // default: " + param_spec.default|tojson }}
-                    {%- endif -%}
-                {%- endif -%}
-                {%- if not loop.last %}
-                    {{- ",\n" }}
-                {%- else %}
-                    {{- "\n" }}
-                {%- endif -%}
-            {%- endfor %}
-            {{- "}) => any;\n\n" }}
-        {%- else -%}
-            {{- "() => any;\n\n" }}
-        {%- endif -%}
+        {{- "\n" }}
+        {{- tool | tojson }}
     {%- endfor %}
-    {{- "} // namespace " + namespace_name }}
-{%- endmacro -%}
-
-{%- macro render_builtin_tools(browser_tool, python_tool) -%}
-    {%- if browser_tool %}
-        {{- "## browser\n\n" }}
-        {{- "// Tool for browsing.\n" }}
-        {{- "// The `cursor` appears in brackets before each browsing display: `[{cursor}]`.\n" }}
-        {{- "// Cite information from the tool using the following format:\n" }}
-        {{- "// `【{cursor}†L{line_start}(-L{line_end})?】`, for example: `【6†L9-L11】` or `【8†L3】`.\n" }}
-        {{- "// Do not quote more than 10 words directly from the tool output.\n" }}
-        {{- "// sources=web (default: web)\n" }}
-        {{- "namespace browser {\n\n" }}
-        {{- "// Searches for information related to `query` and displays `topn` results.\n" }}
-        {{- "type search = (_: {\n" }}
-        {{- "query: string,\n" }}
-        {{- "topn?: number, // default: 10\n" }}
-        {{- "source?: string,\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "// Opens the link `id` from the page indicated by `cursor` starting at line number `loc`, showing `num_lines` lines.\n" }}
-        {{- "// Valid link ids are displayed with the formatting: `【{id}†.*】`.\n" }}
-        {{- "// If `cursor` is not provided, the most recent page is implied.\n" }}
-        {{- "// If `id` is a string, it is treated as a fully qualified URL associated with `source`.\n" }}
-        {{- "// If `loc` is not provided, the viewport will be positioned at the beginning of the document or centered on the most relevant passage, if available.\n" }}
-        {{- "// Use this function without `id` to scroll to a new location of an opened page.\n" }}
-        {{- "type open = (_: {\n" }}
-        {{- "id?: number | string, // default: -1\n" }}
-        {{- "cursor?: number, // default: -1\n" }}
-        {{- "loc?: number, // default: -1\n" }}
-        {{- "num_lines?: number, // default: -1\n" }}
-        {{- "view_source?: boolean, // default: false\n" }}
-        {{- "source?: string,\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "// Finds exact matches of `pattern` in the current page, or the page given by `cursor`.\n" }}
-        {{- "type find = (_: {\n" }}
-        {{- "pattern: string,\n" }}
-        {{- "cursor?: number, // default: -1\n" }}
-        {{- "}) => any;\n\n" }}
-        {{- "} // namespace browser\n\n" }}
-    {%- endif -%}
-
-    {%- if python_tool %}
-        {{- "## python\n\n" }}
-        {{- "Use this tool to execute Python code in your chain of thought. The code will not be shown to the user. This tool should be used for internal reasoning, but not for code that is intended to be visible to the user (e.g. when creating plots, tables, or files).\n\n" }}
-        {{- "When you send a message containing Python code to python, it will be executed in a stateful Jupyter notebook environment. python will respond with the output of the execution or time out after 120.0 seconds. The drive at '/mnt/data' can be used to save and persist user files. Internet access for this session is UNKNOWN. Depends on the cluster.\n\n" }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{#- System Message Construction ============================================ #}
-{%- macro build_system_message() -%}
-    {%- if model_identity is not defined %}
-        {{- "You are ChatGPT, a large language model trained by OpenAI.\n" -}}
-    {%- else %}
-        {{- model_identity }}
-    {%- endif %}
-    {{- "Knowledge cutoff: 2024-06\n" }}
-    {{- "Current date: " + strftime_now("%Y-%m-%d") + "\n\n" }}
-    {%- if reasoning_effort is not defined %}
-        {%- set reasoning_effort = "medium" %}
-    {%- endif %}
-    {{- "Reasoning: " + reasoning_effort + "\n\n" }}
-    {%- if builtin_tools is defined %}
-        {{- "# Tools\n\n" }}
-        {%- set available_builtin_tools = namespace(browser=false, python=false) %}
-        {%- for tool in builtin_tools %}
-            {%- if tool == "browser" %}
-                {%- set available_builtin_tools.browser = true %}
-            {%- elif tool == "python" %}
-                {%- set available_builtin_tools.python = true %}
-            {%- endif %}
-        {%- endfor %}
-        {{- render_builtin_tools(available_builtin_tools.browser, available_builtin_tools.python) }}
-    {%- endif -%}
-    {{- "# Valid channels: analysis, commentary, final. Channel must be included for every message." }}
-    {%- if tools is defined -%}
-        {{- "\nCalls to these tools must go to the commentary channel: 'functions'." }}
-    {%- endif -%}
-{%- endmacro -%}
-
-{#- Main Template Logic ================================================= #}
-{#- Set defaults #}
-
-{#- Render system message #}
-{{- "<|start|>system<|message|>" }}
-{{- build_system_message() }}
-{{- "<|end|>" }}
-
-{#- Extract developer message #}
-{%- if messages[0].role == "developer" or messages[0].role == "system" %}
-    {%- set developer_message = messages[0].content %}
-    {%- set loop_messages = messages[1:] %}
+    {{- "\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 %}
-    {%- set developer_message = "" %}
-    {%- set loop_messages = messages %}
-{%- endif %}
-
-{#- Render developer message #}
-{%- if developer_message or tools %}
-    {{- "<|start|>developer<|message|>" }}
-    {%- if developer_message %}
-        {{- "# Instructions\n\n" }}
-        {{- developer_message }}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
     {%- endif %}
-    {%- if tools -%}
-        {{- "\n\n" }}
-        {{- "# Tools\n\n" }}
-        {{- render_tool_namespace("functions", tools) }}
-    {%- endif -%}
-    {{- "<|end|>" }}
 {%- endif %}
-
-{#- Render messages #}
-{%- set last_tool_call = namespace(name=none) %}
-{%- for message in loop_messages -%}
-    {#- At this point only assistant/user/tool messages should remain #}
-    {%- if message.role == 'assistant' -%}
-        {%- if "tool_calls" in message %}
-            {#- We assume max 1 tool call per message, and so we infer the tool call name #}
-            {#- in "tool" messages from the most recent assistant tool call name #}
-            {%- set tool_call = message.tool_calls[0] %}
-            {%- if tool_call.function %}
-                {%- set tool_call = tool_call.function %}
+{%- 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 %}
-            {%- if message.content %}
-                {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.content + "<|end|>" }}
+        {%- 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 %}
-            {{- "<|start|>assistant to=" }}
-            {{- "functions." + tool_call.name + "<|channel|>commentary json<|message|>" }}
-            {{- tool_call.arguments|tojson }}
-            {{- "<|call|>" }}
-            {%- set last_tool_call.name = tool_call.name %}
-        {%- elif "thinking" in message and loop.last and not add_generation_prompt %}
-            {#- Only render the CoT if the final turn is an assistant turn and add_generation_prompt is false #}
-            {#- This is a situation that should only occur in training, never in inference. #}
-            {{- "<|start|>assistant<|channel|>analysis<|message|>" + message.thinking + "<|end|>" }}
-            {#- <|return|> indicates the end of generation, but <|end|> does not #}
-            {#- <|return|> should never be an input to the model, but we include it as the final token #}
-            {#- when training, so the model learns to emit it. #}
-            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|return|>" }}
-            {%- set last_tool_call.name = none %}
-        {%- elif "thinking" in message %}
-            {#- CoT is dropped during all previous turns, so we never render it for inference #}
-            {{- "<|start|>assistant<|channel|>final<|message|>" + message.content + "<|end|>" }}
-            {%- set last_tool_call.name = none %}
-        {%- elif loop.last and not add_generation_prompt %}
-            {#- <|return|> indicates the end of generation, but <|end|> does not #}
-            {#- <|return|> should never be an input to the model, but we include it as the final token #}
-            {#- when training, so the model learns to emit it. #}
-            {{- "<|start|>assistant<|message|>" + message.content + "<|return|>" }}
         {%- else %}
-            {{- "<|start|>assistant<|message|>" + message.content + "<|end|>" }}
-            {%- set last_tool_call.name = none %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
         {%- endif %}
-    {%- elif message.role == 'tool' -%}
-        {%- if last_tool_call.name is none %}
-            {{- raise_exception("Message has tool role, but there was no previous assistant message with a tool call!") }}
+        {%- 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 %}
-        {{- "<|start|>functions." + last_tool_call.name }}
-        {{- " to=assistant<|channel|>commentary<|message|>" + message.content|tojson + "<|end|>" }}
-    {%- else -%}
-        {{- "<|start|>user<|message|>" + message.content + "<|end|>" }}
-    {%- endif -%}
-{%- endfor -%}
-
-{#- Generation prompt #}
-{%- if add_generation_prompt -%}
-<|start|>assistant
-{%- endif -%}
-{# Copyright 2025-present Unsloth. Apache 2.0 License. Unsloth chat template fixes. Edited from ggml-org & OpenAI #}
+        {{- '<|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 %}

special_tokens_map.json

@@ -1,20 +1,28 @@
 {
-  "bos_token": {
-    "content": "<|startoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": 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|>"
+  ],
   "eos_token": {
-    "content": "<|return|>",
+    "content": "<|im_end|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "pad_token": {
-    "content": "<|reserved_200017|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
-size 27868174
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -1,185 +1,240 @@
 {
+  "add_bos_token": false,
+  "add_prefix_space": false,
   "added_tokens_decoder": {
-    "199998": {
-      "content": "<|startoftext|>",
+    "151643": {
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "199999": {
-      "content": "<|endoftext|>",
+    "151644": {
+      "content": "<|im_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200000": {
-      "content": "<|reserved_200000|>",
+    "151645": {
+      "content": "<|im_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200001": {
-      "content": "<|reserved_200001|>",
+    "151646": {
+      "content": "<|object_ref_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200002": {
-      "content": "<|return|>",
+    "151647": {
+      "content": "<|object_ref_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200003": {
-      "content": "<|constrain|>",
+    "151648": {
+      "content": "<|box_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200004": {
-      "content": "<|reserved_200004|>",
+    "151649": {
+      "content": "<|box_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200005": {
-      "content": "<|channel|>",
+    "151650": {
+      "content": "<|quad_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200006": {
-      "content": "<|start|>",
+    "151651": {
+      "content": "<|quad_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200007": {
-      "content": "<|end|>",
+    "151652": {
+      "content": "<|vision_start|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200008": {
-      "content": "<|message|>",
+    "151653": {
+      "content": "<|vision_end|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200009": {
-      "content": "<|reserved_200009|>",
+    "151654": {
+      "content": "<|vision_pad|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200010": {
-      "content": "<|reserved_200010|>",
+    "151655": {
+      "content": "<|image_pad|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200011": {
-      "content": "<|reserved_200011|>",
+    "151656": {
+      "content": "<|video_pad|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "200012": {
-      "content": "<|call|>",
+    "151657": {
+      "content": "<tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200013": {
-      "content": "<|reserved_200013|>",
+    "151658": {
+      "content": "</tool_call>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200014": {
-      "content": "<|reserved_200014|>",
+    "151659": {
+      "content": "<|fim_prefix|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200015": {
-      "content": "<|reserved_200015|>",
+    "151660": {
+      "content": "<|fim_middle|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200016": {
-      "content": "<|reserved_200016|>",
+    "151661": {
+      "content": "<|fim_suffix|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200017": {
-      "content": "<|reserved_200017|>",
+    "151662": {
+      "content": "<|fim_pad|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "special": false
     },
-    "200018": {
-      "content": "<|endofprompt|>",
+    "151663": {
+      "content": "<|repo_name|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
-      "special": true
+      "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
     }
   },
-  "bos_token": "<|startoftext|>",
+  "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": "<|return|>",
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
   "extra_special_tokens": {},
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
   "model_max_length": 131072,
-  "pad_token": "<|reserved_200017|>",
-  "padding_side": "left",
-  "tokenizer_class": "PreTrainedTokenizerFast",
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null
 }

trainer_state.json

@@ -0,0 +1,1120 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 76,
+  "global_step": 152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02631578947368421,
+      "grad_norm": 0.9123721122741699,
+      "learning_rate": 1e-05,
+      "loss": 1.7529,
+      "step": 1
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": 0.8983409404754639,
+      "learning_rate": 9.93421052631579e-06,
+      "loss": 2.0205,
+      "step": 2
+    },
+    {
+      "epoch": 0.07894736842105263,
+      "grad_norm": 0.7459537386894226,
+      "learning_rate": 9.868421052631579e-06,
+      "loss": 1.938,
+      "step": 3
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.5364267230033875,
+      "learning_rate": 9.80263157894737e-06,
+      "loss": 1.7756,
+      "step": 4
+    },
+    {
+      "epoch": 0.13157894736842105,
+      "grad_norm": 0.5603910088539124,
+      "learning_rate": 9.736842105263159e-06,
+      "loss": 1.7495,
+      "step": 5
+    },
+    {
+      "epoch": 0.15789473684210525,
+      "grad_norm": 0.49162617325782776,
+      "learning_rate": 9.671052631578948e-06,
+      "loss": 1.8455,
+      "step": 6
+    },
+    {
+      "epoch": 0.18421052631578946,
+      "grad_norm": 0.5008453130722046,
+      "learning_rate": 9.605263157894737e-06,
+      "loss": 1.6621,
+      "step": 7
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.5266237258911133,
+      "learning_rate": 9.539473684210528e-06,
+      "loss": 1.7903,
+      "step": 8
+    },
+    {
+      "epoch": 0.23684210526315788,
+      "grad_norm": 0.6560247540473938,
+      "learning_rate": 9.473684210526315e-06,
+      "loss": 1.582,
+      "step": 9
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.3924446702003479,
+      "learning_rate": 9.407894736842106e-06,
+      "loss": 1.7129,
+      "step": 10
+    },
+    {
+      "epoch": 0.2894736842105263,
+      "grad_norm": 0.38711851835250854,
+      "learning_rate": 9.342105263157895e-06,
+      "loss": 1.7773,
+      "step": 11
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.3938468396663666,
+      "learning_rate": 9.276315789473686e-06,
+      "loss": 1.5649,
+      "step": 12
+    },
+    {
+      "epoch": 0.34210526315789475,
+      "grad_norm": 0.36565202474594116,
+      "learning_rate": 9.210526315789474e-06,
+      "loss": 1.6306,
+      "step": 13
+    },
+    {
+      "epoch": 0.3684210526315789,
+      "grad_norm": 0.4620167911052704,
+      "learning_rate": 9.144736842105264e-06,
+      "loss": 1.6184,
+      "step": 14
+    },
+    {
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.33130666613578796,
+      "learning_rate": 9.078947368421054e-06,
+      "loss": 1.623,
+      "step": 15
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.2919524610042572,
+      "learning_rate": 9.013157894736843e-06,
+      "loss": 1.6318,
+      "step": 16
+    },
+    {
+      "epoch": 0.4473684210526316,
+      "grad_norm": 0.2672816812992096,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 1.4897,
+      "step": 17
+    },
+    {
+      "epoch": 0.47368421052631576,
+      "grad_norm": 0.23821978271007538,
+      "learning_rate": 8.881578947368423e-06,
+      "loss": 1.428,
+      "step": 18
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.21208712458610535,
+      "learning_rate": 8.81578947368421e-06,
+      "loss": 1.4756,
+      "step": 19
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.2554440498352051,
+      "learning_rate": 8.750000000000001e-06,
+      "loss": 1.5552,
+      "step": 20
+    },
+    {
+      "epoch": 0.5526315789473685,
+      "grad_norm": 0.20846055448055267,
+      "learning_rate": 8.68421052631579e-06,
+      "loss": 1.5527,
+      "step": 21
+    },
+    {
+      "epoch": 0.5789473684210527,
+      "grad_norm": 0.22391115128993988,
+      "learning_rate": 8.61842105263158e-06,
+      "loss": 1.5237,
+      "step": 22
+    },
+    {
+      "epoch": 0.6052631578947368,
+      "grad_norm": 0.2024792730808258,
+      "learning_rate": 8.552631578947368e-06,
+      "loss": 1.459,
+      "step": 23
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.2103537917137146,
+      "learning_rate": 8.486842105263159e-06,
+      "loss": 1.5869,
+      "step": 24
+    },
+    {
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.1935657262802124,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.4313,
+      "step": 25
+    },
+    {
+      "epoch": 0.6842105263157895,
+      "grad_norm": 0.18945100903511047,
+      "learning_rate": 8.355263157894737e-06,
+      "loss": 1.4692,
+      "step": 26
+    },
+    {
+      "epoch": 0.7105263157894737,
+      "grad_norm": 0.2018207460641861,
+      "learning_rate": 8.289473684210526e-06,
+      "loss": 1.4473,
+      "step": 27
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.17049378156661987,
+      "learning_rate": 8.223684210526316e-06,
+      "loss": 1.3296,
+      "step": 28
+    },
+    {
+      "epoch": 0.7631578947368421,
+      "grad_norm": 0.17862842977046967,
+      "learning_rate": 8.157894736842106e-06,
+      "loss": 1.2607,
+      "step": 29
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.20279452204704285,
+      "learning_rate": 8.092105263157896e-06,
+      "loss": 1.3848,
+      "step": 30
+    },
+    {
+      "epoch": 0.8157894736842105,
+      "grad_norm": 0.17397917807102203,
+      "learning_rate": 8.026315789473685e-06,
+      "loss": 1.3027,
+      "step": 31
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.23914802074432373,
+      "learning_rate": 7.960526315789474e-06,
+      "loss": 1.5098,
+      "step": 32
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 0.18806089460849762,
+      "learning_rate": 7.894736842105265e-06,
+      "loss": 1.2754,
+      "step": 33
+    },
+    {
+      "epoch": 0.8947368421052632,
+      "grad_norm": 0.2042052298784256,
+      "learning_rate": 7.828947368421054e-06,
+      "loss": 1.5605,
+      "step": 34
+    },
+    {
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.1831723302602768,
+      "learning_rate": 7.763157894736843e-06,
+      "loss": 1.3862,
+      "step": 35
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.1900983452796936,
+      "learning_rate": 7.697368421052632e-06,
+      "loss": 1.3682,
+      "step": 36
+    },
+    {
+      "epoch": 0.9736842105263158,
+      "grad_norm": 0.1751386821269989,
+      "learning_rate": 7.631578947368423e-06,
+      "loss": 1.4795,
+      "step": 37
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.19076912105083466,
+      "learning_rate": 7.565789473684211e-06,
+      "loss": 1.4268,
+      "step": 38
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 0.17538294196128845,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.2935,
+      "step": 39
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.1990729719400406,
+      "learning_rate": 7.43421052631579e-06,
+      "loss": 1.4525,
+      "step": 40
+    },
+    {
+      "epoch": 1.0789473684210527,
+      "grad_norm": 0.19373203814029694,
+      "learning_rate": 7.368421052631579e-06,
+      "loss": 1.3889,
+      "step": 41
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 0.17557767033576965,
+      "learning_rate": 7.302631578947369e-06,
+      "loss": 1.3292,
+      "step": 42
+    },
+    {
+      "epoch": 1.131578947368421,
+      "grad_norm": 0.18259677290916443,
+      "learning_rate": 7.236842105263158e-06,
+      "loss": 1.2814,
+      "step": 43
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.18624745309352875,
+      "learning_rate": 7.1710526315789475e-06,
+      "loss": 1.4247,
+      "step": 44
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.16235268115997314,
+      "learning_rate": 7.1052631578947375e-06,
+      "loss": 1.271,
+      "step": 45
+    },
+    {
+      "epoch": 1.2105263157894737,
+      "grad_norm": 0.18120981752872467,
+      "learning_rate": 7.0394736842105274e-06,
+      "loss": 1.4043,
+      "step": 46
+    },
+    {
+      "epoch": 1.236842105263158,
+      "grad_norm": 0.2193688303232193,
+      "learning_rate": 6.973684210526316e-06,
+      "loss": 1.1313,
+      "step": 47
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.18220637738704681,
+      "learning_rate": 6.907894736842106e-06,
+      "loss": 1.376,
+      "step": 48
+    },
+    {
+      "epoch": 1.2894736842105263,
+      "grad_norm": 0.1826276183128357,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 1.458,
+      "step": 49
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.2493559569120407,
+      "learning_rate": 6.776315789473686e-06,
+      "loss": 1.2534,
+      "step": 50
+    },
+    {
+      "epoch": 1.3421052631578947,
+      "grad_norm": 0.17839138209819794,
+      "learning_rate": 6.710526315789474e-06,
+      "loss": 1.3435,
+      "step": 51
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.22518493235111237,
+      "learning_rate": 6.644736842105264e-06,
+      "loss": 1.2935,
+      "step": 52
+    },
+    {
+      "checkpoint_runtime": 10.1043
+    },
+    {
+      "epoch": 1.3947368421052633,
+      "grad_norm": 0.1906924694776535,
+      "learning_rate": 6.578947368421054e-06,
+      "loss": 1.3525,
+      "step": 53
+    },
+    {
+      "epoch": 1.4210526315789473,
+      "grad_norm": 0.19758851826190948,
+      "learning_rate": 6.513157894736842e-06,
+      "loss": 1.3856,
+      "step": 54
+    },
+    {
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.18283262848854065,
+      "learning_rate": 6.447368421052632e-06,
+      "loss": 1.2532,
+      "step": 55
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.19298750162124634,
+      "learning_rate": 6.381578947368422e-06,
+      "loss": 1.1985,
+      "step": 56
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.17387087643146515,
+      "learning_rate": 6.31578947368421e-06,
+      "loss": 1.2573,
+      "step": 57
+    },
+    {
+      "epoch": 1.526315789473684,
+      "grad_norm": 0.22176223993301392,
+      "learning_rate": 6.25e-06,
+      "loss": 1.3278,
+      "step": 58
+    },
+    {
+      "epoch": 1.5526315789473686,
+      "grad_norm": 0.18737094104290009,
+      "learning_rate": 6.18421052631579e-06,
+      "loss": 1.3545,
+      "step": 59
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.21818137168884277,
+      "learning_rate": 6.118421052631579e-06,
+      "loss": 1.2976,
+      "step": 60
+    },
+    {
+      "epoch": 1.6052631578947367,
+      "grad_norm": 0.19866132736206055,
+      "learning_rate": 6.0526315789473685e-06,
+      "loss": 1.2627,
+      "step": 61
+    },
+    {
+      "epoch": 1.631578947368421,
+      "grad_norm": 0.21948541700839996,
+      "learning_rate": 5.9868421052631585e-06,
+      "loss": 1.3801,
+      "step": 62
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 0.18909035623073578,
+      "learning_rate": 5.921052631578948e-06,
+      "loss": 1.2484,
+      "step": 63
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.19033916294574738,
+      "learning_rate": 5.855263157894738e-06,
+      "loss": 1.2832,
+      "step": 64
+    },
+    {
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.20355014503002167,
+      "learning_rate": 5.789473684210527e-06,
+      "loss": 1.2362,
+      "step": 65
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 0.17357026040554047,
+      "learning_rate": 5.723684210526316e-06,
+      "loss": 1.1641,
+      "step": 66
+    },
+    {
+      "epoch": 1.763157894736842,
+      "grad_norm": 0.19439999759197235,
+      "learning_rate": 5.657894736842106e-06,
+      "loss": 1.082,
+      "step": 67
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.22951634228229523,
+      "learning_rate": 5.592105263157896e-06,
+      "loss": 1.2029,
+      "step": 68
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 0.1897413432598114,
+      "learning_rate": 5.526315789473685e-06,
+      "loss": 1.127,
+      "step": 69
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.2506878077983856,
+      "learning_rate": 5.460526315789474e-06,
+      "loss": 1.2786,
+      "step": 70
+    },
+    {
+      "epoch": 1.868421052631579,
+      "grad_norm": 0.19912667572498322,
+      "learning_rate": 5.394736842105264e-06,
+      "loss": 1.0957,
+      "step": 71
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 1.4676445722579956,
+      "learning_rate": 5.328947368421054e-06,
+      "loss": 1.3501,
+      "step": 72
+    },
+    {
+      "epoch": 1.9210526315789473,
+      "grad_norm": 0.201414093375206,
+      "learning_rate": 5.263157894736842e-06,
+      "loss": 1.2012,
+      "step": 73
+    },
+    {
+      "epoch": 1.9473684210526314,
+      "grad_norm": 0.19307729601860046,
+      "learning_rate": 5.197368421052632e-06,
+      "loss": 1.1748,
+      "step": 74
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.19274558126926422,
+      "learning_rate": 5.131578947368422e-06,
+      "loss": 1.313,
+      "step": 75
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.20288924872875214,
+      "learning_rate": 5.0657894736842104e-06,
+      "loss": 1.2534,
+      "step": 76
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.17578125,
+      "eval_runtime": 3.5221,
+      "eval_samples_per_second": 3.407,
+      "eval_steps_per_second": 0.568,
+      "step": 76
+    },
+    {
+      "epoch": 2.026315789473684,
+      "grad_norm": 0.19196660816669464,
+      "learning_rate": 5e-06,
+      "loss": 1.1514,
+      "step": 77
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 0.22189833223819733,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 1.2638,
+      "step": 78
+    },
+    {
+      "epoch": 2.0789473684210527,
+      "grad_norm": 0.21822911500930786,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 1.2109,
+      "step": 79
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.2068079113960266,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 1.179,
+      "step": 80
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 0.2942705750465393,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 1.1239,
+      "step": 81
+    },
+    {
+      "epoch": 2.1578947368421053,
+      "grad_norm": 0.23848527669906616,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 1.2626,
+      "step": 82
+    },
+    {
+      "epoch": 2.1842105263157894,
+      "grad_norm": 0.1883735954761505,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 1.1343,
+      "step": 83
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.20841026306152344,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 1.2786,
+      "step": 84
+    },
+    {
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.24563977122306824,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.9895,
+      "step": 85
+    },
+    {
+      "epoch": 2.263157894736842,
+      "grad_norm": 0.19508451223373413,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 1.2197,
+      "step": 86
+    },
+    {
+      "epoch": 2.2894736842105265,
+      "grad_norm": 0.2005009800195694,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 1.3101,
+      "step": 87
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.21326693892478943,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 1.1106,
+      "step": 88
+    },
+    {
+      "epoch": 2.3421052631578947,
+      "grad_norm": 0.20623892545700073,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.2069,
+      "step": 89
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.2533697783946991,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 1.1436,
+      "step": 90
+    },
+    {
+      "epoch": 2.3947368421052633,
+      "grad_norm": 0.2188979834318161,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 1.2021,
+      "step": 91
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.21808868646621704,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 1.2418,
+      "step": 92
+    },
+    {
+      "epoch": 2.4473684210526314,
+      "grad_norm": 0.20212087035179138,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 1.1102,
+      "step": 93
+    },
+    {
+      "epoch": 2.473684210526316,
+      "grad_norm": 0.2139948606491089,
+      "learning_rate": 3.8815789473684214e-06,
+      "loss": 1.0573,
+      "step": 94
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.21474292874336243,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 1.1265,
+      "step": 95
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.23335693776607513,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 1.1888,
+      "step": 96
+    },
+    {
+      "epoch": 2.5526315789473686,
+      "grad_norm": 0.20745357871055603,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 1.2212,
+      "step": 97
+    },
+    {
+      "epoch": 2.5789473684210527,
+      "grad_norm": 0.24392454326152802,
+      "learning_rate": 3.618421052631579e-06,
+      "loss": 1.1482,
+      "step": 98
+    },
+    {
+      "epoch": 2.6052631578947367,
+      "grad_norm": 0.209051251411438,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 1.1431,
+      "step": 99
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.24735654890537262,
+      "learning_rate": 3.486842105263158e-06,
+      "loss": 1.2396,
+      "step": 100
+    },
+    {
+      "epoch": 2.6578947368421053,
+      "grad_norm": 0.19793781638145447,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 1.1342,
+      "step": 101
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 0.21070927381515503,
+      "learning_rate": 3.355263157894737e-06,
+      "loss": 1.1704,
+      "step": 102
+    },
+    {
+      "checkpoint_runtime": 9.4822
+    },
+    {
+      "epoch": 2.7105263157894735,
+      "grad_norm": 0.22601282596588135,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 1.1041,
+      "step": 103
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.18559959530830383,
+      "learning_rate": 3.223684210526316e-06,
+      "loss": 1.0654,
+      "step": 104
+    },
+    {
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.20749028027057648,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.9834,
+      "step": 105
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 0.2508399784564972,
+      "learning_rate": 3.092105263157895e-06,
+      "loss": 1.0941,
+      "step": 106
+    },
+    {
+      "epoch": 2.8157894736842106,
+      "grad_norm": 0.21029452979564667,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 1.0352,
+      "step": 107
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.27152472734451294,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 1.1492,
+      "step": 108
+    },
+    {
+      "epoch": 2.8684210526315788,
+      "grad_norm": 0.2187647819519043,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 1.0068,
+      "step": 109
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.23925845324993134,
+      "learning_rate": 2.828947368421053e-06,
+      "loss": 1.2441,
+      "step": 110
+    },
+    {
+      "epoch": 2.9210526315789473,
+      "grad_norm": 0.21557359397411346,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 1.1035,
+      "step": 111
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.2115062177181244,
+      "learning_rate": 2.697368421052632e-06,
+      "loss": 1.084,
+      "step": 112
+    },
+    {
+      "epoch": 2.973684210526316,
+      "grad_norm": 0.21911245584487915,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 1.2256,
+      "step": 113
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.21688233315944672,
+      "learning_rate": 2.565789473684211e-06,
+      "loss": 1.165,
+      "step": 114
+    },
+    {
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.20714174211025238,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0786,
+      "step": 115
+    },
+    {
+      "epoch": 3.0526315789473686,
+      "grad_norm": 0.23801325261592865,
+      "learning_rate": 2.4342105263157898e-06,
+      "loss": 1.1616,
+      "step": 116
+    },
+    {
+      "epoch": 3.0789473684210527,
+      "grad_norm": 0.2522694766521454,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 1.1205,
+      "step": 117
+    },
+    {
+      "epoch": 3.1052631578947367,
+      "grad_norm": 0.20447932183742523,
+      "learning_rate": 2.3026315789473684e-06,
+      "loss": 1.1024,
+      "step": 118
+    },
+    {
+      "epoch": 3.1315789473684212,
+      "grad_norm": 0.22387726604938507,
+      "learning_rate": 2.236842105263158e-06,
+      "loss": 1.0515,
+      "step": 119
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.2203892469406128,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 1.1839,
+      "step": 120
+    },
+    {
+      "epoch": 3.1842105263157894,
+      "grad_norm": 0.19983014464378357,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 1.0659,
+      "step": 121
+    },
+    {
+      "epoch": 3.2105263157894735,
+      "grad_norm": 0.2277001142501831,
+      "learning_rate": 2.0394736842105266e-06,
+      "loss": 1.2161,
+      "step": 122
+    },
+    {
+      "epoch": 3.236842105263158,
+      "grad_norm": 0.26377543807029724,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.925,
+      "step": 123
+    },
+    {
+      "epoch": 3.263157894736842,
+      "grad_norm": 0.21232622861862183,
+      "learning_rate": 1.9078947368421057e-06,
+      "loss": 1.144,
+      "step": 124
+    },
+    {
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.2160305678844452,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 1.2456,
+      "step": 125
+    },
+    {
+      "epoch": 3.3157894736842106,
+      "grad_norm": 0.2347312867641449,
+      "learning_rate": 1.7763157894736844e-06,
+      "loss": 1.0468,
+      "step": 126
+    },
+    {
+      "epoch": 3.3421052631578947,
+      "grad_norm": 0.22175875306129456,
+      "learning_rate": 1.710526315789474e-06,
+      "loss": 1.1398,
+      "step": 127
+    },
+    {
+      "epoch": 3.3684210526315788,
+      "grad_norm": 0.26978111267089844,
+      "learning_rate": 1.6447368421052635e-06,
+      "loss": 1.0754,
+      "step": 128
+    },
+    {
+      "epoch": 3.3947368421052633,
+      "grad_norm": 0.2348111867904663,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 1.1348,
+      "step": 129
+    },
+    {
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.23943249881267548,
+      "learning_rate": 1.5131578947368421e-06,
+      "loss": 1.1715,
+      "step": 130
+    },
+    {
+      "epoch": 3.4473684210526314,
+      "grad_norm": 0.2244543582201004,
+      "learning_rate": 1.4473684210526317e-06,
+      "loss": 1.0444,
+      "step": 131
+    },
+    {
+      "epoch": 3.473684210526316,
+      "grad_norm": 0.2498081922531128,
+      "learning_rate": 1.3815789473684212e-06,
+      "loss": 0.9928,
+      "step": 132
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.21809686720371246,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 1.0674,
+      "step": 133
+    },
+    {
+      "epoch": 3.526315789473684,
+      "grad_norm": 0.2573719620704651,
+      "learning_rate": 1.25e-06,
+      "loss": 1.1315,
+      "step": 134
+    },
+    {
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.22611169517040253,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 1.1646,
+      "step": 135
+    },
+    {
+      "epoch": 3.5789473684210527,
+      "grad_norm": 0.25931963324546814,
+      "learning_rate": 1.118421052631579e-06,
+      "loss": 1.0789,
+      "step": 136
+    },
+    {
+      "epoch": 3.6052631578947367,
+      "grad_norm": 0.2301693558692932,
+      "learning_rate": 1.0526315789473685e-06,
+      "loss": 1.0928,
+      "step": 137
+    },
+    {
+      "epoch": 3.6315789473684212,
+      "grad_norm": 0.2776806354522705,
+      "learning_rate": 9.86842105263158e-07,
+      "loss": 1.1768,
+      "step": 138
+    },
+    {
+      "epoch": 3.6578947368421053,
+      "grad_norm": 0.2093764841556549,
+      "learning_rate": 9.210526315789474e-07,
+      "loss": 1.0848,
+      "step": 139
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.21807806193828583,
+      "learning_rate": 8.55263157894737e-07,
+      "loss": 1.1221,
+      "step": 140
+    },
+    {
+      "epoch": 3.7105263157894735,
+      "grad_norm": 0.2526063621044159,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 1.05,
+      "step": 141
+    },
+    {
+      "epoch": 3.736842105263158,
+      "grad_norm": 0.19926978647708893,
+      "learning_rate": 7.236842105263158e-07,
+      "loss": 1.0264,
+      "step": 142
+    },
+    {
+      "epoch": 3.763157894736842,
+      "grad_norm": 0.22158919274806976,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 0.9414,
+      "step": 143
+    },
+    {
+      "epoch": 3.7894736842105265,
+      "grad_norm": 0.26375311613082886,
+      "learning_rate": 5.921052631578947e-07,
+      "loss": 1.0459,
+      "step": 144
+    },
+    {
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.21970221400260925,
+      "learning_rate": 5.263157894736843e-07,
+      "loss": 0.9985,
+      "step": 145
+    },
+    {
+      "epoch": 3.8421052631578947,
+      "grad_norm": 0.2868686318397522,
+      "learning_rate": 4.605263157894737e-07,
+      "loss": 1.0981,
+      "step": 146
+    },
+    {
+      "epoch": 3.8684210526315788,
+      "grad_norm": 0.22975504398345947,
+      "learning_rate": 3.9473684210526315e-07,
+      "loss": 0.9683,
+      "step": 147
+    },
+    {
+      "epoch": 3.8947368421052633,
+      "grad_norm": 0.25351837277412415,
+      "learning_rate": 3.2894736842105264e-07,
+      "loss": 1.1978,
+      "step": 148
+    },
+    {
+      "epoch": 3.9210526315789473,
+      "grad_norm": 0.23104619979858398,
+      "learning_rate": 2.6315789473684213e-07,
+      "loss": 1.0684,
+      "step": 149
+    },
+    {
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.22691509127616882,
+      "learning_rate": 1.9736842105263157e-07,
+      "loss": 1.0488,
+      "step": 150
+    },
+    {
+      "epoch": 3.973684210526316,
+      "grad_norm": 0.21638430655002594,
+      "learning_rate": 1.3157894736842107e-07,
+      "loss": 1.1958,
+      "step": 151
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.22461865842342377,
+      "learning_rate": 6.578947368421053e-08,
+      "loss": 1.1362,
+      "step": 152
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.07098388671875,
+      "eval_runtime": 2.6493,
+      "eval_samples_per_second": 4.529,
+      "eval_steps_per_second": 0.755,
+      "step": 152
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 152,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.96512299022418e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}