Training in progress, step 250, checkpoint

checkpoint-250/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/gemma-4-E2B-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/gemma-4-E2B-it
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.20.0

checkpoint-250/adapter_config.json

@@ -0,0 +1,54 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-4-E2B-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": [
+    "vision_tower",
+    "audio_tower",
+    "multi_modal_projector"
+  ],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoint-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a5cb1c30dd5d8e2d14e7b350581437b326c4e24c0dbf100d47818240fcd2448
+size 119545752

checkpoint-250/chat_template.jinja

@@ -0,0 +1,386 @@
+{#
+  Template: Google Gemma 4 Canonical Chat Template
+  Author: Google Gemma Engineering Team
+  Published: 2026-07-09
+  Context: Fixed tool-calling loops, turn closures, and thinking content-ordering.
+#}
+{%- macro format_parameters(properties, required, filter_keys=false) -%}
+    {%- set standard_keys = ['description', 'type', 'properties', 'required', 'nullable'] -%}
+    {%- set ns = namespace(found_first=false) -%}
+    {%- for key, value in properties | dictsort -%}
+        {%- set add_comma = false -%}
+        {%- if not filter_keys or key not in standard_keys -%}
+            {%- if ns.found_first %},{% endif -%}
+            {%- set ns.found_first = true -%}
+            {{ key }}:{
+            {%- if value['description'] -%}
+                description:<|"|>{{ value['description'] }}<|"|>
+                {%- set add_comma = true -%}
+            {%- endif -%}
+            {%- if value['type'] | upper == 'STRING' -%}
+                {%- if value['enum'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    enum:{{ format_argument(value['enum']) }}
+                {%- endif -%}
+            {%- elif value['type'] | upper == 'ARRAY' -%}
+                {%- if value['items'] is mapping and value['items'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    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 -%}
+                                    <|"|>{{- req_item -}}<|"|>
+                                    {%- 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 -%}
+            {%- if value['nullable'] %}
+                {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                nullable:true
+            {%- endif -%}
+            {%- if value['type'] | upper == 'OBJECT' -%}
+                {%- if value['properties'] is defined and value['properties'] is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value['properties'], value['required'] | default([])) -}}
+                    }
+                {%- elif value is mapping -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    properties:{
+                    {{- format_parameters(value, value['required'] | default([]), filter_keys=true) -}}
+                    }
+                {%- endif -%}
+                {%- if value['required'] -%}
+                    {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+                    required:[
+                    {%- for item in value['required'] | default([]) -%}
+                        <|"|>{{- item -}}<|"|>
+                        {%- if not loop.last %},{% endif -%}
+                    {%- endfor -%}
+                    ]
+                {%- endif -%}
+            {%- endif -%}
+            {%- if add_comma %},{%- else -%} {%- set add_comma = true -%} {% endif -%}
+            type:<|"|>{{ value['type'] | upper }}<|"|>}
+        {%- endif -%}
+    {%- endfor -%}
+{%- endmacro -%}
+{%- macro format_function_declaration(tool_data) -%}
+    declaration:{{- tool_data['function']['name'] -}}{description:<|"|>{{- tool_data['function']['description'] -}}<|"|>
+    {%- 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'] -%}
+                <|"|>{{- item -}}<|"|>
+                {{- ',' if not loop.last -}}
+            {%- endfor -%}
+            ],
+        {%- endif -%}
+        {%- if params['type'] -%}
+            type:<|"|>{{- params['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    {%- if 'response' in tool_data['function'] -%}
+        {%- set response_declaration = tool_data['function']['response'] -%}
+        ,response:{
+        {%- if response_declaration['description'] -%}
+            description:<|"|>{{- response_declaration['description'] -}}<|"|>,
+        {%- endif -%}
+        {%- if response_declaration['type'] | upper == 'OBJECT' -%}
+            type:<|"|>{{- response_declaration['type'] | upper -}}<|"|>}
+        {%- endif -%}
+    {%- endif -%}
+    }
+{%- endmacro -%}
+{%- macro format_argument(argument, escape_keys=True) -%}
+    {%- if argument is none -%}
+        {{- 'null' -}}
+    {%- elif argument is string -%}
+        {{- '<|"|>' + argument + '<|"|>' -}}
+    {%- elif argument is boolean -%}
+        {{- 'true' if argument else 'false' -}}
+    {%- 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 -%}
+                {{- '<|"|>' + key + '<|"|>' -}}
+            {%- 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 -%}
+{%- macro strip_thinking(text) -%}
+    {%- set ns = namespace(result='') -%}
+    {%- for part in text.split('<channel|>') -%}
+        {%- if '<|channel>' in part -%}
+            {%- set ns.result = ns.result + part.split('<|channel>')[0] -%}
+        {%- else -%}
+            {%- set ns.result = ns.result + part -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {{- ns.result | trim -}}
+{%- endmacro -%}
+
+{%- macro format_tool_response_block(tool_name, response) -%}
+    {{- '<|tool_response>' -}}
+    {%- if response is mapping -%}
+        {{- 'response:' + tool_name + '{' -}}
+        {%- for key, value in response | dictsort -%}
+            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+            {%- if not loop.last %},{% endif -%}
+        {%- endfor -%}
+        {{- '}' -}}
+    {%- else -%}
+        {{- 'response:' + tool_name + '{value:' + format_argument(response, escape_keys=False) + '}' -}}
+    {%- endif -%}
+    {{- '<tool_response|>' -}}
+{%- endmacro -%}
+
+{#- ===== SETUP ===== -#}
+{%- set ns = namespace(prev_message_type=None, prev_non_tool_role=None) -%}
+{%- set loop_messages = messages -%}
+{%- set enable_thinking = enable_thinking | default(false) -%}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+{{- bos_token -}}
+{#- Handle System/Tool Definitions Block -#}
+{%- if enable_thinking or tools or (messages and messages[0]['role'] in ['system', 'developer']) -%}
+    {{- '<|turn>system\n' -}}
+    {#- Inject Thinking token at the very top of the FIRST system turn -#}
+    {%- if enable_thinking -%}
+        {{- '<|think|>\n' -}}
+        {%- set ns.prev_message_type = 'think' -%}
+    {%- endif -%}
+    {%- if messages and messages[0]['role'] in ['system', 'developer'] -%}
+        {%- if messages[0]['content'] is string -%}
+            {{- messages[0]['content'] | trim -}}
+        {%- elif messages[0]['content'] is sequence -%}
+            {%- for item in messages[0]['content'] -%}
+                {{- item['text'] | trim + ' '-}}
+            {%- endfor -%}
+        {%- endif -%}
+        {%- set loop_messages = messages[1:] -%}
+    {%- endif -%}
+    {%- if tools -%}
+        {%- for tool in tools %}
+            {{- '<|tool>' -}}
+            {{- format_function_declaration(tool) | trim -}}
+            {{- '<tool|>' -}}
+        {%- endfor %}
+        {%- set ns.prev_message_type = 'tool' -%}
+    {%- endif -%}
+    {{- '<turn|>\n' -}}
+{%- endif %}
+
+{#- Pre-scan: find last user message index for reasoning guard -#}
+{%- set ns_turn = namespace(last_user_idx=-1) -%}
+{%- for i in range(loop_messages | length) -%}
+    {%- if loop_messages[i]['role'] == 'user' -%}
+        {%- set ns_turn.last_user_idx = i -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{#- Loop through messages -#}
+{%- for message in loop_messages -%}
+    {%- if message['role'] != 'tool' -%}
+    {%- set ns.prev_message_type = None -%}
+    {%- set role = 'model' if message['role'] == 'assistant' else message['role'] -%}
+    {#- Detect continuation using tracked state — O(1) instead of O(n) backward scan -#}
+    {%- set continue_same_model_turn = (role == 'model' and ns.prev_non_tool_role == 'assistant') -%}
+    {%- if not continue_same_model_turn -%}
+        {{- '<|turn>' + role + '\n' }}
+    {%- endif -%}
+
+    {#- Render reasoning/reasoning_content as thinking channel -#}
+    {%- set thinking_text = message.get('reasoning') or message.get('reasoning_content') -%}
+    {%- set thinking_gate = (loop.index0 > ns_turn.last_user_idx) or (preserve_thinking and message.get('tool_calls')) -%}
+    {%- if thinking_text and thinking_gate -%}
+        {{- '<|channel>thought\n' + thinking_text + '\n<channel|>' -}}
+    {%- endif -%}
+
+            {%- if message.get('tool_calls') -%}
+                {%- for tool_call in message.get('tool_calls') -%}
+                    {%- set function = tool_call['function'] -%}
+                    {{- '<|tool_call>call:' + function['name'] + '{' -}}
+                    {%- if function['arguments'] is mapping -%}
+                        {%- set ns_args = namespace(found_first=false) -%}
+                        {%- for key, value in function['arguments'] | dictsort -%}
+                            {%- if ns_args.found_first %},{% endif -%}
+                            {%- set ns_args.found_first = true -%}
+                            {{- key -}}:{{- format_argument(value, escape_keys=False) -}}
+                        {%- endfor -%}
+                    {%- elif function['arguments'] is none -%}
+                    {%- else -%}
+                        {{- raise_exception(
+                            "chat_template: tool_calls[].function.arguments must be a "
+                            "JSON object (mapping), not a string. Deserialize arguments "
+                            "before passing to the template."
+                        ) -}}
+                    {%- endif -%}
+                    {{- '}<tool_call|>' -}}
+                {%- endfor -%}
+                {%- set ns.prev_message_type = 'tool_call' -%}
+            {%- endif -%}
+
+            {%- set ns_tr_out = namespace(flag=false) -%}
+            {%- if message.get('tool_responses') -%}
+                {#- Legacy: tool_responses embedded on the assistant message (Google/Gemma native) -#}
+                {%- for tool_response in message.get('tool_responses') -%}
+                    {{- format_tool_response_block(tool_response['name'] | default('unknown', true), tool_response['response']) -}}
+                    {%- set ns_tr_out.flag = true -%}
+                    {%- set ns.prev_message_type = 'tool_response' -%}
+                {%- endfor -%}
+            {%- elif message.get('tool_calls') -%}
+                {#- OpenAI Chat Completions: forward-scan consecutive role:tool messages -#}
+                {%- set ns_tool_scan = namespace(stopped=false) -%}
+                {%- for k in range(loop.index0 + 1, loop_messages | length) -%}
+                    {%- if ns_tool_scan.stopped -%}
+                    {%- elif loop_messages[k]['role'] != 'tool' -%}
+                        {%- set ns_tool_scan.stopped = true -%}
+                    {%- else -%}
+                        {%- set follow = loop_messages[k] -%}
+                        {#- Resolve tool_call_id to function name -#}
+                        {%- set ns_tname = namespace(name=follow.get('name') or 'unknown') -%}
+                        {%- for tc in message.get('tool_calls') -%}
+                            {%- if tc.get('id') == follow.get('tool_call_id') -%}
+                                {%- set ns_tname.name = tc['function']['name'] -%}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {#- Handle content as string or content-parts array -#}
+                        {%- set tool_body = follow.get('content') -%}
+                        {%- if tool_body is string -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- elif tool_body is sequence and tool_body is not string -%}
+                            {%- set ns_txt = namespace(s='') -%}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') == 'text' -%}
+                                    {%- set ns_txt.s = ns_txt.s + (part.get('text') | default('')) -%}
+                                {%- endif -%}
+                            {%- endfor -%}
+                            {{- format_tool_response_block(ns_tname.name, ns_txt.s) -}}
+                            {%- for part in tool_body -%}
+                                {%- if part.get('type') in ['image', 'image_url'] -%}
+                                    {{- '<|image|>' -}}
+                                {%- elif part.get('type') in ['audio', 'input_audio'] -%}
+                                    {{- '<|audio|>' -}}
+                                {%- elif part.get('type') == 'video' -%}
+                                    {{- '<|video|>' -}}
+                                {%- endif -%}
+                            {%- endfor -%}
+                        {%- else -%}
+                            {{- format_tool_response_block(ns_tname.name, tool_body) -}}
+                        {%- endif -%}
+                        {%- set ns_tr_out.flag = true -%}
+                        {%- set ns.prev_message_type = 'tool_response' -%}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+
+            {%- set captured_content -%}
+            {%- if message.get('content') is string -%}
+                {%- if role == 'model' -%}
+                    {{- strip_thinking(message['content']) -}}
+                {%- else -%}
+                    {{- message['content'] | trim -}}
+                {%- endif -%}
+            {%- elif message.get('content') is sequence -%}
+                {%- for item in message['content'] -%}
+                    {%- if item.get('type') == 'text' -%}
+                        {%- if role == 'model' -%}
+                            {{- strip_thinking(item['text']) -}}
+                        {%- else -%}
+                            {{- item['text'] | trim -}}
+                        {%- endif -%}
+                    {%- elif item.get('type') in ['image', 'image_url'] -%}
+                        {{- '<|image|>' -}}
+                    {%- elif item.get('type') in ['audio', 'input_audio'] -%}
+                        {{- '<|audio|>' -}}
+                    {%- elif item.get('type') == 'video' -%}
+                        {{- '<|video|>' -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- endif -%}
+            {%- endset -%}
+
+            {{- captured_content -}}
+            {%- set has_content = captured_content | trim | length > 0 -%}
+
+        {#- Forward-scan: find next non-tool message role for continuation detection -#}
+        {%- set next_nt = namespace(role=None, found=false) -%}
+        {%- for j in range(loop.index0 + 1, loop_messages | length) -%}
+            {%- if not next_nt.found -%}
+                {%- if loop_messages[j]['role'] != 'tool' -%}
+                    {%- set next_nt.role = loop_messages[j]['role'] -%}
+                    {%- set next_nt.found = true -%}
+                {%- endif -%}
+            {%- endif -%}
+        {%- endfor -%}
+
+        {%- set continues_into_next = (
+            role == 'model'
+            and next_nt.role == 'assistant'
+            and (not message.get('tool_calls') or ns_tr_out.flag)
+        ) -%}
+
+        {%- if ns.prev_message_type == 'tool_call' and not ns_tr_out.flag -%}
+            {{- '<|tool_response>' -}}
+        {%- elif continues_into_next -%}
+        {%- elif not (ns_tr_out.flag and not has_content and not next_nt.found) -%}
+            {{- '<turn|>\n' -}}
+        {%- endif -%}
+
+    {#- Track previous non-tool role for next iteration (avoids O(n) backward scan) -#}
+    {%- set ns.prev_non_tool_role = message['role'] -%}
+    {%- endif -%}
+{%- endfor -%}
+
+{%- if add_generation_prompt -%}
+    {%- if ns.prev_message_type != 'tool_response' and ns.prev_message_type != 'tool_call' -%}
+        {{- '<|turn>model\n' -}}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95e5b48bb701326b4720c6644eddc307c99d125c05fa1badfac903b30c0045dc
+size 98635341

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b43968218bce499dbcab43c58dbb095ae0fd894d5156fd10c2a892a95b49a8b
+size 14645

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00f439b3bbbaf893aa89ab85b53f2e1f7d537de5eeeea6d27e16aba519e7b34d
+size 1465

checkpoint-250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8d3a0ce36466ccc1278bf987df5f71db1719b9ca6b4118264f45cb627bfe0f
+size 32169626

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,142 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<eos>",
+  "padding_side": "right",
+  "processor_class": "Gemma4Processor",
+  "response_schema": {
+    "properties": {
+      "content": {
+        "type": "string"
+      },
+      "role": {
+        "const": "assistant"
+      },
+      "thinking": {
+        "type": "string"
+      },
+      "tool_calls": {
+        "items": {
+          "properties": {
+            "function": {
+              "properties": {
+                "arguments": {
+                  "additionalProperties": {},
+                  "type": "object",
+                  "x-parser": "gemma4-tool-call"
+                },
+                "name": {
+                  "type": "string"
+                }
+              },
+              "type": "object",
+              "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
+            },
+            "type": {
+              "const": "function"
+            }
+          },
+          "type": "object"
+        },
+        "type": "array",
+        "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
+      }
+    },
+    "type": "object",
+    "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
+  },
+  "response_template": {
+    "defaults": {
+      "role": "assistant"
+    },
+    "fields": {
+      "content": {
+        "close": [
+          "<turn|>",
+          "<|tool_response>",
+          "<eos>"
+        ],
+        "content": "text"
+      },
+      "thinking": {
+        "close": "<channel|>",
+        "content": "text",
+        "open": "<|channel>thought\n"
+      },
+      "tool_calls": {
+        "close": "<tool_call|>",
+        "content": "json",
+        "content_args": {
+          "string_delims": [
+            [
+              "<|\"|>",
+              "<|\"|>"
+            ]
+          ],
+          "unquoted_keys": true
+        },
+        "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
+        "repeats": true,
+        "transform": {
+          "function": {
+            "arguments": "{content}",
+            "name": "{name}"
+          },
+          "type": "function"
+        }
+      }
+    },
+    "start_anchor": [
+      "<|turn>model\n",
+      "<tool_response|>"
+    ]
+  },
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,339 @@
+{
+  "best_global_step": 200,
+  "best_metric": 0.024746960029006004,
+  "best_model_checkpoint": "/kaggle/working/gemma4_e2b_outputs/checkpoint-200",
+  "epoch": 0.8424599831508003,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.03442627163240104,
+      "epoch": 0.03369839932603201,
+      "grad_norm": 0.57421875,
+      "learning_rate": 4.6285714285714284e-05,
+      "loss": 0.30414247512817383,
+      "mean_token_accuracy": 0.9633298896253109,
+      "num_tokens": 50202.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.036702575445815455,
+      "epoch": 0.06739679865206402,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 9.771428571428572e-05,
+      "loss": 0.02679154872894287,
+      "mean_token_accuracy": 0.9942228332161903,
+      "num_tokens": 99730.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.023526186634990155,
+      "epoch": 0.10109519797809605,
+      "grad_norm": 0.189453125,
+      "learning_rate": 0.00014914285714285716,
+      "loss": 0.03063507378101349,
+      "mean_token_accuracy": 0.9914997152984142,
+      "num_tokens": 150097.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.034747927097487266,
+      "epoch": 0.13479359730412804,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017997726000648073,
+      "loss": 0.0251019150018692,
+      "mean_token_accuracy": 0.9931103173643351,
+      "num_tokens": 198701.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.016794490450593003,
+      "epoch": 0.16849199663016007,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.0001797215670311433,
+      "loss": 0.027158683538436888,
+      "mean_token_accuracy": 0.9932276383042336,
+      "num_tokens": 251032.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.16849199663016007,
+      "eval_entropy": 0.022378485068695636,
+      "eval_loss": 0.031730424612760544,
+      "eval_mean_token_accuracy": 0.9921912817470178,
+      "eval_num_tokens": 251032.0,
+      "eval_runtime": 1126.4408,
+      "eval_samples_per_second": 1.799,
+      "eval_steps_per_second": 0.899,
+      "step": 50
+    },
+    {
+      "entropy": 0.02238693693652749,
+      "epoch": 0.2021903959561921,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00017918256616680084,
+      "loss": 0.022676032781600953,
+      "mean_token_accuracy": 0.9933203727006912,
+      "num_tokens": 301297.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.02536057697416254,
+      "epoch": 0.2358887952822241,
+      "grad_norm": 0.1953125,
+      "learning_rate": 0.00017836195938101938,
+      "loss": 0.02103605568408966,
+      "mean_token_accuracy": 0.9937991909682751,
+      "num_tokens": 349637.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.024386808862982435,
+      "epoch": 0.2695871946082561,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 0.00017726233784985462,
+      "loss": 0.024811160564422608,
+      "mean_token_accuracy": 0.9928908865898848,
+      "num_tokens": 399870.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.02778970852796192,
+      "epoch": 0.3032855939342881,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017588717377586623,
+      "loss": 0.03330623209476471,
+      "mean_token_accuracy": 0.9904133033007383,
+      "num_tokens": 449477.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.023341893833276117,
+      "epoch": 0.33698399326032014,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.00017424080942417207,
+      "loss": 0.025586703419685365,
+      "mean_token_accuracy": 0.9928323667496443,
+      "num_tokens": 498229.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.33698399326032014,
+      "eval_entropy": 0.0210638620780726,
+      "eval_loss": 0.03126470372080803,
+      "eval_mean_token_accuracy": 0.9927122755323675,
+      "eval_num_tokens": 498229.0,
+      "eval_runtime": 1124.2212,
+      "eval_samples_per_second": 1.802,
+      "eval_steps_per_second": 0.901,
+      "step": 100
+    },
+    {
+      "entropy": 0.022127612936856167,
+      "epoch": 0.37068239258635216,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001723284434111633,
+      "loss": 0.025175514817237853,
+      "mean_token_accuracy": 0.9937295001000166,
+      "num_tokens": 553163.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.025844440628861775,
+      "epoch": 0.4043807919123842,
+      "grad_norm": 0.107421875,
+      "learning_rate": 0.00017015611428917556,
+      "loss": 0.02075621634721756,
+      "mean_token_accuracy": 0.994851179793477,
+      "num_tokens": 602833.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.017262498397030868,
+      "epoch": 0.43807919123841615,
+      "grad_norm": 0.224609375,
+      "learning_rate": 0.00016773068147894944,
+      "loss": 0.02128828167915344,
+      "mean_token_accuracy": 0.9945652581751346,
+      "num_tokens": 650313.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.02044138053424831,
+      "epoch": 0.4717775905644482,
+      "grad_norm": 0.357421875,
+      "learning_rate": 0.00016505980361008902,
+      "loss": 0.018230150640010833,
+      "mean_token_accuracy": 0.9947165582329035,
+      "num_tokens": 697785.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.016532328606263035,
+      "epoch": 0.5054759898904801,
+      "grad_norm": 0.228515625,
+      "learning_rate": 0.00016215191433791105,
+      "loss": 0.02196011245250702,
+      "mean_token_accuracy": 0.9940924983471632,
+      "num_tokens": 746296.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.5054759898904801,
+      "eval_entropy": 0.021309930168988408,
+      "eval_loss": 0.02765325829386711,
+      "eval_mean_token_accuracy": 0.9929286667531005,
+      "eval_num_tokens": 746296.0,
+      "eval_runtime": 1125.2103,
+      "eval_samples_per_second": 1.801,
+      "eval_steps_per_second": 0.9,
+      "step": 150
+    },
+    {
+      "entropy": 0.02324409563480003,
+      "epoch": 0.5391743892165122,
+      "grad_norm": 0.36328125,
+      "learning_rate": 0.00015901619571304635,
+      "loss": 0.024296788871288298,
+      "mean_token_accuracy": 0.9937251776456832,
+      "num_tokens": 795578.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.02200790760543896,
+      "epoch": 0.5728727885425442,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.00015566254918788285,
+      "loss": 0.020977529883384704,
+      "mean_token_accuracy": 0.994451267644763,
+      "num_tokens": 845253.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.017312285865955346,
+      "epoch": 0.6065711878685762,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 0.00015210156435140063,
+      "loss": 0.01916155368089676,
+      "mean_token_accuracy": 0.9945312373340129,
+      "num_tokens": 895137.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.01355354385341343,
+      "epoch": 0.6402695871946082,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 0.00014834448549112372,
+      "loss": 0.016632051765918733,
+      "mean_token_accuracy": 0.9952114578336477,
+      "num_tokens": 945391.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.01753964945983171,
+      "epoch": 0.6739679865206403,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 0.0001444031760877731,
+      "loss": 0.016346196830272674,
+      "mean_token_accuracy": 0.9948002852499485,
+      "num_tokens": 994601.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.6739679865206403,
+      "eval_entropy": 0.02103348611687381,
+      "eval_loss": 0.024746960029006004,
+      "eval_mean_token_accuracy": 0.9939268553833618,
+      "eval_num_tokens": 994601.0,
+      "eval_runtime": 1126.1962,
+      "eval_samples_per_second": 1.799,
+      "eval_steps_per_second": 0.899,
+      "step": 200
+    },
+    {
+      "entropy": 0.020208403906508465,
+      "epoch": 0.7076663858466723,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.0001402900813547342,
+      "loss": 0.023702555894851686,
+      "mean_token_accuracy": 0.9935556031763554,
+      "num_tokens": 1042508.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.02361248063043604,
+      "epoch": 0.7413647851727043,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.00013601818894062547,
+      "loss": 0.02297559231519699,
+      "mean_token_accuracy": 0.9938195463269949,
+      "num_tokens": 1094683.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.02179833457048517,
+      "epoch": 0.7750631844987363,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 0.00013160098791905475,
+      "loss": 0.02227169871330261,
+      "mean_token_accuracy": 0.9937427151948214,
+      "num_tokens": 1143379.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.02089707843479118,
+      "epoch": 0.8087615838247684,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 0.0001270524261950592,
+      "loss": 0.0160829097032547,
+      "mean_token_accuracy": 0.9948678724467754,
+      "num_tokens": 1191313.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.012493419923021064,
+      "epoch": 0.8424599831508003,
+      "grad_norm": 0.154296875,
+      "learning_rate": 0.00012238686646272312,
+      "loss": 0.016340985894203186,
+      "mean_token_accuracy": 0.9960907097905874,
+      "num_tokens": 1240950.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.8424599831508003,
+      "eval_entropy": 0.014308816084650821,
+      "eval_loss": 0.025563491508364677,
+      "eval_mean_token_accuracy": 0.9939537474339477,
+      "eval_num_tokens": 1240950.0,
+      "eval_runtime": 1125.9371,
+      "eval_samples_per_second": 1.799,
+      "eval_steps_per_second": 0.9,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 594,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.29682838124032e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545d9e9114a70c72a1e35f789611908870e987f7b59e7bebee5bd7f7fe1286d8
+size 5777