Upload finetuned FunctionGemma for Italian function calling

.gitattributes

@@ -33,3 +33,8 @@ 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
+checkpoint-154/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-308/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-77/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: transformers
+model_name: outputs
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for outputs
+
+This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.0.0
+- Transformers: 5.5.1
+- Pytorch: 2.11.0
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-154/chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-154/config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.1",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-154/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    50,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.1"
+}

checkpoint-154/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fb534a4891753c3ebb1a9de98b341c468d2af48358952ad356dba5d9a6c73a
+size 536223056

checkpoint-154/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6462a18da18cd52b1d0a0207bad998d42dc86e0f7df8492a865e5145bb25c45
+size 1072594443

checkpoint-154/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718a0f3db00824213036a2c0441849791319b7d9cf189065873bb26a7020738e
+size 14645

checkpoint-154/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e83b8ffb0782b40f36dd8317e0757ffe7f134c174b4c60d0bd74dcd9d506e7
+size 1465

checkpoint-154/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

checkpoint-154/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>",
+    "sfr_token": "<start_function_response>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sfr_token": "<start_function_response>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-154/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 50,
+  "global_step": 154,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8290567851066589,
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.388394947836278e-06,
+      "loss": 0.11062156677246093,
+      "mean_token_accuracy": 0.9778690934181213,
+      "num_tokens": 389732.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "eval_entropy": 0.7784549756483599,
+      "eval_loss": 0.03614399954676628,
+      "eval_mean_token_accuracy": 0.9917981918756064,
+      "eval_num_tokens": 389732.0,
+      "eval_runtime": 12.9713,
+      "eval_samples_per_second": 23.513,
+      "eval_steps_per_second": 5.936,
+      "step": 50
+    },
+    {
+      "entropy": 0.7608775209834557,
+      "epoch": 1.3021346469622332,
+      "grad_norm": 0.6796875,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.022044627666473388,
+      "mean_token_accuracy": 0.9940849557784374,
+      "num_tokens": 771178.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.3021346469622332,
+      "eval_entropy": 0.7180899474527929,
+      "eval_loss": 0.019734159111976624,
+      "eval_mean_token_accuracy": 0.9949120081864394,
+      "eval_num_tokens": 771178.0,
+      "eval_runtime": 13.0354,
+      "eval_samples_per_second": 23.398,
+      "eval_steps_per_second": 5.907,
+      "step": 100
+    },
+    {
+      "entropy": 0.7120695394277573,
+      "epoch": 1.9589490968801315,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.25488887635095e-06,
+      "loss": 0.013736556768417358,
+      "mean_token_accuracy": 0.9967586588859558,
+      "num_tokens": 1165084.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.9589490968801315,
+      "eval_entropy": 0.6842893903905695,
+      "eval_loss": 0.013124481774866581,
+      "eval_mean_token_accuracy": 0.9965388542645938,
+      "eval_num_tokens": 1165084.0,
+      "eval_runtime": 13.0811,
+      "eval_samples_per_second": 23.316,
+      "eval_steps_per_second": 5.886,
+      "step": 150
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1006601818940928.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-154/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5363ce9d99dd9dbf1bc2c5ff6c4b0ce553147005c7381cbde8798f93d5971fb
+size 5649

checkpoint-231/chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-231/config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.1",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-231/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    50,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.1"
+}

checkpoint-231/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55b9632e5cf5540c78cd35b1e0e220c54e92aff80343623998b0b23885f9b141
+size 536223056

checkpoint-231/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea1cca6a4544a5b70c2fd53427f81667a461bda7b06d55017ebe5de993aa40c
+size 1072594443

checkpoint-231/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f196323d7423b60f8e4ceb7dbf8715ee326c0d068e5ff164f13c63b279b9f1a0
+size 14645

checkpoint-231/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2c2b23c7e4352465f050c1d63ce488c1582e84995535f53d01e1408547e53ea
+size 1465

checkpoint-231/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

checkpoint-231/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>",
+    "sfr_token": "<start_function_response>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sfr_token": "<start_function_response>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-231/trainer_state.json

@@ -0,0 +1,118 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 231,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8290567851066589,
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.388394947836278e-06,
+      "loss": 0.11062156677246093,
+      "mean_token_accuracy": 0.9778690934181213,
+      "num_tokens": 389732.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "eval_entropy": 0.7784549756483599,
+      "eval_loss": 0.03614399954676628,
+      "eval_mean_token_accuracy": 0.9917981918756064,
+      "eval_num_tokens": 389732.0,
+      "eval_runtime": 12.9713,
+      "eval_samples_per_second": 23.513,
+      "eval_steps_per_second": 5.936,
+      "step": 50
+    },
+    {
+      "entropy": 0.7608775209834557,
+      "epoch": 1.3021346469622332,
+      "grad_norm": 0.6796875,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.022044627666473388,
+      "mean_token_accuracy": 0.9940849557784374,
+      "num_tokens": 771178.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.3021346469622332,
+      "eval_entropy": 0.7180899474527929,
+      "eval_loss": 0.019734159111976624,
+      "eval_mean_token_accuracy": 0.9949120081864394,
+      "eval_num_tokens": 771178.0,
+      "eval_runtime": 13.0354,
+      "eval_samples_per_second": 23.398,
+      "eval_steps_per_second": 5.907,
+      "step": 100
+    },
+    {
+      "entropy": 0.7120695394277573,
+      "epoch": 1.9589490968801315,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.25488887635095e-06,
+      "loss": 0.013736556768417358,
+      "mean_token_accuracy": 0.9967586588859558,
+      "num_tokens": 1165084.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.9589490968801315,
+      "eval_entropy": 0.6842893903905695,
+      "eval_loss": 0.013124481774866581,
+      "eval_mean_token_accuracy": 0.9965388542645938,
+      "eval_num_tokens": 1165084.0,
+      "eval_runtime": 13.0811,
+      "eval_samples_per_second": 23.316,
+      "eval_steps_per_second": 5.886,
+      "step": 150
+    },
+    {
+      "entropy": 0.6924438694961198,
+      "epoch": 2.6042692939244665,
+      "grad_norm": 0.423828125,
+      "learning_rate": 2.7847456480060476e-06,
+      "loss": 0.008616942763328552,
+      "mean_token_accuracy": 0.9980061287795011,
+      "num_tokens": 1550848.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.6042692939244665,
+      "eval_entropy": 0.678199358961799,
+      "eval_loss": 0.012337171472609043,
+      "eval_mean_token_accuracy": 0.996950343831793,
+      "eval_num_tokens": 1550848.0,
+      "eval_runtime": 13.0386,
+      "eval_samples_per_second": 23.392,
+      "eval_steps_per_second": 5.906,
+      "step": 200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1508776468555776.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-231/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5363ce9d99dd9dbf1bc2c5ff6c4b0ce553147005c7381cbde8798f93d5971fb
+size 5649

checkpoint-308/chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-308/config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.1",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-308/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    50,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.1"
+}

checkpoint-308/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdad25a78c297aab9ec2b809949a6f0b1968f7a6a09d486343d48fe3f5c51da
+size 536223056

checkpoint-308/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:251ca04ead3677dedb4846271e2205f3277a2eca493a068019cb64e3e4754342
+size 1072594443

checkpoint-308/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea11996454b5587fcf33ae0ab5cf14b2031bf5f53f8c2ed5a48e87de31e29c84
+size 14645

checkpoint-308/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46bf8c059ac0682006a9531cce7258bd0ef62fc0ab3b4eceb1892efacaf6680b
+size 1465

checkpoint-308/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

checkpoint-308/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>",
+    "sfr_token": "<start_function_response>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sfr_token": "<start_function_response>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-308/trainer_state.json

@@ -0,0 +1,171 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 50,
+  "global_step": 308,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8290567851066589,
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.388394947836278e-06,
+      "loss": 0.11062156677246093,
+      "mean_token_accuracy": 0.9778690934181213,
+      "num_tokens": 389732.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "eval_entropy": 0.7784549756483599,
+      "eval_loss": 0.03614399954676628,
+      "eval_mean_token_accuracy": 0.9917981918756064,
+      "eval_num_tokens": 389732.0,
+      "eval_runtime": 12.9713,
+      "eval_samples_per_second": 23.513,
+      "eval_steps_per_second": 5.936,
+      "step": 50
+    },
+    {
+      "entropy": 0.7608775209834557,
+      "epoch": 1.3021346469622332,
+      "grad_norm": 0.6796875,
+      "learning_rate": 7.660160382576683e-06,
+      "loss": 0.022044627666473388,
+      "mean_token_accuracy": 0.9940849557784374,
+      "num_tokens": 771178.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.3021346469622332,
+      "eval_entropy": 0.7180899474527929,
+      "eval_loss": 0.019734159111976624,
+      "eval_mean_token_accuracy": 0.9949120081864394,
+      "eval_num_tokens": 771178.0,
+      "eval_runtime": 13.0354,
+      "eval_samples_per_second": 23.398,
+      "eval_steps_per_second": 5.907,
+      "step": 100
+    },
+    {
+      "entropy": 0.7120695394277573,
+      "epoch": 1.9589490968801315,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.25488887635095e-06,
+      "loss": 0.013736556768417358,
+      "mean_token_accuracy": 0.9967586588859558,
+      "num_tokens": 1165084.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.9589490968801315,
+      "eval_entropy": 0.6842893903905695,
+      "eval_loss": 0.013124481774866581,
+      "eval_mean_token_accuracy": 0.9965388542645938,
+      "eval_num_tokens": 1165084.0,
+      "eval_runtime": 13.0811,
+      "eval_samples_per_second": 23.316,
+      "eval_steps_per_second": 5.886,
+      "step": 150
+    },
+    {
+      "entropy": 0.6924438694961198,
+      "epoch": 2.6042692939244665,
+      "grad_norm": 0.423828125,
+      "learning_rate": 2.7847456480060476e-06,
+      "loss": 0.008616942763328552,
+      "mean_token_accuracy": 0.9980061287795011,
+      "num_tokens": 1550848.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.6042692939244665,
+      "eval_entropy": 0.678199358961799,
+      "eval_loss": 0.012337171472609043,
+      "eval_mean_token_accuracy": 0.996950343831793,
+      "eval_num_tokens": 1550848.0,
+      "eval_runtime": 13.0386,
+      "eval_samples_per_second": 23.392,
+      "eval_steps_per_second": 5.906,
+      "step": 200
+    },
+    {
+      "entropy": 0.6876007438312657,
+      "epoch": 3.2495894909688015,
+      "grad_norm": 0.6484375,
+      "learning_rate": 8.784064067287057e-07,
+      "loss": 0.008523799180984497,
+      "mean_token_accuracy": 0.9980273214915326,
+      "num_tokens": 1935501.0,
+      "step": 250
+    },
+    {
+      "epoch": 3.2495894909688015,
+      "eval_entropy": 0.6709755380432327,
+      "eval_loss": 0.011750386096537113,
+      "eval_mean_token_accuracy": 0.9970997378423616,
+      "eval_num_tokens": 1935501.0,
+      "eval_runtime": 13.0005,
+      "eval_samples_per_second": 23.461,
+      "eval_steps_per_second": 5.923,
+      "step": 250
+    },
+    {
+      "entropy": 0.6889240379631519,
+      "epoch": 3.9064039408866993,
+      "grad_norm": 0.6015625,
+      "learning_rate": 2.1053210266875346e-08,
+      "loss": 0.00826053500175476,
+      "mean_token_accuracy": 0.9980920545756817,
+      "num_tokens": 2322603.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.9064039408866993,
+      "eval_entropy": 0.6722380197667456,
+      "eval_loss": 0.011939619667828083,
+      "eval_mean_token_accuracy": 0.996877890128594,
+      "eval_num_tokens": 2322603.0,
+      "eval_runtime": 13.2474,
+      "eval_samples_per_second": 23.023,
+      "eval_steps_per_second": 5.812,
+      "step": 300
+    },
+    {
+      "epoch": 4.0,
+      "eval_entropy": 0.6724205961475125,
+      "eval_loss": 0.01190057210624218,
+      "eval_mean_token_accuracy": 0.9969809620411365,
+      "eval_num_tokens": 2378596.0,
+      "eval_runtime": 13.6271,
+      "eval_samples_per_second": 22.382,
+      "eval_steps_per_second": 5.651,
+      "step": 308
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2009014625409792.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-308/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5363ce9d99dd9dbf1bc2c5ff6c4b0ce553147005c7381cbde8798f93d5971fb
+size 5649

checkpoint-77/chat_template.jinja

@@ -0,0 +1,279 @@
+{%- macro format_parameters(properties, required) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- if key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{- key }}:{description:<escape>{{ value['description'] }}<escape>
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    ,enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'OBJECT' -%}
+                ,properties:{
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                {%- elif value is mapping -%}
+                    {{- format_parameters(value, value['required'] | default([])) -}}
+                {%- endif -%}
+                }
+                {%- if value['required'] -%}
+                    ,required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <escape>{{- item -}}<escape>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    ,items:{
+                    {%- set ns_items = namespace(found_first=false) -%}
+                    {%- for item_key, item_value in value['items'] | dictsort -%}
+                        {%- if item_value is not none -%}
+                            {%- if ns_items.found_first %},{% endif -%}
+                            {%- set ns_items.found_first = true -%}
+                            {%- if item_key == 'properties' -%}
+                                properties:{
+                                {%- if item_value is mapping -%}
+                                    {{- format_parameters(item_value, value['items']['required'] | default([])) -}}
+                                {%- endif -%}
+                                }
+                            {%- elif item_key == 'required' -%}
+                                required:[
+                                {%- for req_item in item_value -%}
+                                    <escape>{{- req_item -}}<escape>
+                                    {%- if not loop.last %},{% endif -%}
+                                {%- endfor -%}
+                                ]
+                            {%- elif item_key == 'type' -%}
+                                {%- if item_value is string -%}
+                                    type:{{ format_argument(item_value | upper) }}
+                                {%- else -%}
+                                    type:{{ format_argument(item_value | map('upper') | list) }}
+                                {%- endif -%}
+                            {%- else -%}
+                                {{ item_key }}:{{ format_argument(item_value) }}
+                            {%- endif -%}
+                        {%- endif -%}
+                    {%- endfor -%}
+                    }
+                {%- endif -%}
+            {%- endif -%}
+            ,type:<escape>{{ value['type'] | upper }}<escape>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{% macro format_function_declaration(tool_data) -%}
+declaration:{{- tool_data['function']['name'] -}}
+{description:<escape>{{- tool_data['function']['description'] -}}<escape>
+{%- set params = tool_data['function']['parameters'] -%}
+{%- if params -%}
+    ,parameters:{
+    {%- if params['properties'] -%}
+        properties:{ {{- format_parameters(params['properties'], params['required']) -}} },
+    {%- endif -%}
+    {%- if params['required'] -%}
+        required:[
+        {%- for item in params['required'] -%}
+            <escape>{{- item -}}<escape>
+            {{- ',' if not loop.last -}}
+        {%- endfor -%}
+        ],
+    {%- endif -%}
+    {%- if params['type'] -%}
+        type:<escape>{{- params['type'] | upper -}}<escape>}
+    {%- endif -%}
+{%- endif -%}
+}
+{%- endmacro -%}
+{% macro format_argument(argument, escape_keys=True) -%}
+{%- if argument is string -%}
+    {{- '<escape>' + argument + '<escape>' -}}
+{%- elif argument is boolean -%}
+    {%- if argument -%}
+        {{- 'true' -}}
+    {%- else -%}
+        {{- 'false' -}}
+    {%- endif -%}
+{%- elif argument is mapping -%}
+    {{- '{' -}}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in argument | dictsort -%}
+        {%- if ns.found_first %},{% endif -%}
+        {%- set ns.found_first = true -%}
+        {%- if escape_keys -%}
+            {{- '<escape>' + key + '<escape>' -}}
+        {%- else -%}
+            {{- key -}}
+        {%- endif -%}
+        :{{- format_argument(value, escape_keys=escape_keys) -}}
+    {%- endfor -%}
+    {{- '}' -}}
+{%- elif argument is sequence -%}
+    {{- '[' -}}
+    {%- for item in argument -%}
+        {{- format_argument(item, escape_keys=escape_keys) -}}
+        {%- if not loop.last %},{% endif -%}
+    {%- endfor -%}
+    {{- ']' -}}
+{%- else -%}
+    {{- argument -}}
+{%- endif -%}
+{%- endmacro -%}
+{{ bos_token }}
+{%- set ns = namespace(prev_message_type=None) -%}
+{#- Tool Declarations -#}
+{%- set loop_messages = messages -%}
+{%- if tools or messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+    {{- '<start_of_turn>developer\n' -}}
+    {%- if messages[0]['role'] == 'system' or messages[0]['role'] == 'developer' -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {%- if item['type'] == 'text' -%}
+                    {{- item['text'] | trim -}}
+                {%- endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<start_function_declaration>' -}}
+            {{- format_function_declaration(tool) | trim }}
+            {{- '<end_function_declaration>' -}}
+        {%- endfor %}
+    {%- endif -%}
+    {{- '<end_of_turn>\n' }}
+{%- endif %}
+{#- Loop through messages. -#}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {#- Rename "assistant" to "model". -#}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {%- if role != 'tool' -%}
+        {%- if ns.prev_message_type != 'tool_response' -%}
+            {{- '<start_of_turn>' + role + '\n' }}
+        {%- endif -%}
+        {%- set ns.prev_message_type = None -%}
+        {%- if 'content' in message and message['content'] is not none -%}
+            {%- if message['content'] is string -%}
+                {{ message['content'] | trim }}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item['type'] == 'image' -%}
+                        {{ '<start_of_image>' }}
+                    {%- elif item['type'] == 'text' -%}
+                        {{ item['text'] | trim }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in user/assistant message") }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'content' -%}
+        {%- endif -%}
+        {%- if 'tool_calls' in message and message['tool_calls'] and message['tool_calls'] is iterable -%}
+            {#- Tool Calls -#}
+            {%- for tool_call in message['tool_calls'] -%}
+                {% set function = tool_call['function'] %}
+                {{-  '<start_function_call>call:' + function['name'] + '{' -}}
+                {%- if 'arguments' in function -%}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns.found_first %},{% endif -%}
+                            {%- set ns.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is string -%}
+                        {# This handles string-JSON, just in case #}
+                    {{ function['arguments'] }}
+                    {%- endif %}
+                {%- endif -%}
+                {{- '}<end_function_call>' -}}
+            {%- endfor -%}
+            {%- if loop.last -%}
+                {{ '<start_function_response>' }}
+            {%- endif -%}
+            {%- set ns.prev_message_type = 'tool_call' -%}
+        {%- endif -%}
+    {%- else -%}
+        {#- Tool Responses -#}
+        {%- if 'content' in message and message['content'] -%}
+            {%- if message['content'] is mapping -%}
+                {%- if 'name' in message['content'] and 'response' in message['content'] -%}
+                    {{ '<start_function_response>response:' + message['content']['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content']['response'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- elif 'name' in message -%}
+                    {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                    {%- set response_ns = namespace(found_first=false) -%}
+                    {%- for key, value in message['content'] | dictsort -%}
+                        {%- if response_ns.found_first %},{% endif -%}
+                        {%- set response_ns.found_first = true -%}
+                        {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                    {%- endfor -%}
+                    {{- '}<end_function_response>' -}}
+                {%- else -%}
+                    {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                {%- endif -%}
+            {%- elif message['content'] is string -%}
+                {%- if 'name' in message -%}
+                     {{ '<start_function_response>response:' + message['name'] | trim + '{value:' + format_argument(message['content'], escape_keys=False) + '}<end_function_response>' }}
+                {%- else -%}
+                     {{ raise_exception("Invalid tool response: 'name' must be provided.") }}
+                {%- endif -%}
+            {%- elif message['content'] is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item is mapping -%}
+                        {%- if 'name' in item and 'response' in item -%}
+                            {{ '<start_function_response>response:' + item['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item['response'] | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- elif 'name' in message -%}
+                            {{ '<start_function_response>response:' + message['name'] | trim + '{' }}
+                            {%- set response_ns = namespace(found_first=false) -%}
+                            {%- for key, value in item | dictsort -%}
+                                {%- if response_ns.found_first %},{% endif -%}
+                                {%- set response_ns.found_first = true -%}
+                                {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                            {%- endfor -%}
+                            {{- '}<end_function_response>' -}}
+                        {%- else -%}
+                            {{ raise_exception("Invalid tool response mapping: must contain 'name' and 'response' keys, or 'name' must be in the message.") }}
+                        {%- endif -%}
+                    {%- else -%}
+                        {{ raise_exception("Invalid tool response message: multiple responses must all be mappings") }}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{ raise_exception("Invalid content type in tool message: must be mapping, sequence of mappings, or string.") }}
+            {%- endif -%}
+        {%- endif -%}
+        {%- set ns.prev_message_type = 'tool_response' -%}
+    {%- endif -%}
+    {%- if ns.prev_message_type not in ['tool_call', 'tool_response'] -%}
+        {{ '<end_of_turn>\n' }}
+    {%- endif -%}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' -%}
+        {{- '<start_of_turn>model\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-77/config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.1",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

checkpoint-77/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    50,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.1"
+}

checkpoint-77/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394256bfee05b42e5f2df4d6d70a8cc4803914120d528782a9e2906a5796970f
+size 536223056

checkpoint-77/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb7d1d4bed0c5d4d8629496b7d67361f2a17dec7dd93d23d32503c6aa170495
+size 1072594443

checkpoint-77/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-77/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41252c4518652c4d654b361ca3ba34bc3d27477f1e95b590d2d97028117662b4
+size 1465

checkpoint-77/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80d7f800b949accd7eb940bac75e642f9468e4df157403032a55bf54ed23b650
+size 33384898

checkpoint-77/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>",
+    "sfr_token": "<start_function_response>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "sfr_token": "<start_function_response>",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-77/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50,
+  "global_step": 77,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8290567851066589,
+      "epoch": 0.6568144499178982,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.388394947836278e-06,
+      "loss": 0.11062156677246093,
+      "mean_token_accuracy": 0.9778690934181213,
+      "num_tokens": 389732.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.6568144499178982,
+      "eval_entropy": 0.7784549756483599,
+      "eval_loss": 0.03614399954676628,
+      "eval_mean_token_accuracy": 0.9917981918756064,
+      "eval_num_tokens": 389732.0,
+      "eval_runtime": 12.9713,
+      "eval_samples_per_second": 23.513,
+      "eval_steps_per_second": 5.936,
+      "step": 50
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 308,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 503646432269568.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-77/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5363ce9d99dd9dbf1bc2c5ff6c4b0ce553147005c7381cbde8798f93d5971fb
+size 5649

config.json

@@ -0,0 +1,62 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 640,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "full_attention": {
+      "rope_theta": 1000000.0,
+      "rope_type": "default"
+    },
+    "sliding_attention": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "sliding_window": 512,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.5.1",
+  "use_bidirectional_attention": false,
+  "use_cache": false,
+  "vocab_size": 262144
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1,
+    50,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.5.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fdad25a78c297aab9ec2b809949a6f0b1968f7a6a09d486343d48fe3f5c51da
+size 536223056