Upload full trainer checkpoint (last@step100)

.gitattributes

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

README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/gemma-4-31B-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/gemma-4-31B-it
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# 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 0.19.1

adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Gemma4ForConditionalGeneration",
+    "parent_library": "transformers.models.gemma4.modeling_gemma4",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/gemma-4-31B-it",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_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
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b23bbe6ba9858d91159158d5c98152c09c5725f3f3c3d8dd6e71330d2672cb3
+size 3917867504

chat_template.jinja

@@ -0,0 +1,389 @@
+{%- 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 -%}
+                    {%- elif function['arguments'] is string -%}
+                        {#- Pre-serialized args (e.g. an OpenAI JSON string). We cannot JSON-parse
+                            portably in-template, so render non-fatally instead of erroring. Strip an
+                            outer {...} so it composes with the DSL braces rather than double-wrapping.
+                            Prefer passing arguments as a mapping for exact Gemma DSL. -#}
+                        {%- set argstr = function['arguments'] | trim -%}
+                        {%- if argstr[:1] == '{' and argstr[-1:] == '}' -%}
+                            {{- argstr[1:-1] -}}
+                        {%- else -%}
+                            {{- function['arguments'] -}}
+                        {%- endif -%}
+                    {%- 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' -}}
+        {%- if not enable_thinking -%}
+            {{- '<|channel>thought\n<channel|>' -}}
+        {%- endif -%}
+    {%- elif ns.prev_message_type == 'tool_response' and enable_thinking -%}
+        {{- '<|channel>thought\n' -}}
+    {%- endif -%}
+{%- endif -%}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcf6f7cb97b058963b899310bfee5d5562b819683643cb65a1117551b95ea21d
+size 1990451125

processor_config.json

@@ -0,0 +1,75 @@
+{
+  "audio_ms_per_token": 40,
+  "audio_seq_length": 750,
+  "feature_extractor": {
+    "dither": 0.0,
+    "feature_extractor_type": "Gemma4AudioFeatureExtractor",
+    "feature_size": 128,
+    "fft_length": 512,
+    "fft_overdrive": false,
+    "frame_length": 320,
+    "hop_length": 160,
+    "input_scale_factor": 1.0,
+    "max_frequency": 8000.0,
+    "mel_floor": 0.001,
+    "min_frequency": 0.0,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "per_bin_mean": null,
+    "per_bin_stddev": null,
+    "preemphasis": 0.0,
+    "preemphasis_htk_flavor": true,
+    "return_attention_mask": true,
+    "sampling_rate": 16000
+  },
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": false,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_processor_type": "Gemma4ImageProcessor",
+    "image_seq_length": 280,
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 280,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098
+  },
+  "image_seq_length": 280,
+  "processor_class": "Gemma4Processor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "image_mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "image_std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "max_soft_tokens": 70,
+    "num_frames": 32,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "video_processor_type": "Gemma4VideoProcessor"
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27978b0c0a2d70a6d9e24fba0f2ed928bba9b47aecb6cc92523c33dd4a9bc29f
+size 14917

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d4883ea9e9e4170ef036b08f27772e01a500be9d13e3c9492d90b6357d7e8c6
+size 14917

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a73d4133c71f756233b3e098aa68f7d3a84edc8fa9a53f12fdd88ac4016e0c
+size 1465

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,290 @@
+{
+  "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": "<turn|>",
+  "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": 262144,
+  "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": "<pad>",
+  "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\\>)?"
+  },
+  "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>",
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "46": {
+      "content": "<|tool>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "47": {
+      "content": "<tool|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "48": {
+      "content": "<|tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "49": {
+      "content": "<tool_call|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "50": {
+      "content": "<|tool_response>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "51": {
+      "content": "<tool_response|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "52": {
+      "content": "<|\"|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "98": {
+      "content": "<|think|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "100": {
+      "content": "<|channel>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "101": {
+      "content": "<channel|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "105": {
+      "content": "<|turn>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "106": {
+      "content": "<turn|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "255999": {
+      "content": "<|image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "256000": {
+      "content": "<|audio>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258880": {
+      "content": "<|image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258881": {
+      "content": "<|audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258882": {
+      "content": "<image|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258883": {
+      "content": "<audio|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "258884": {
+      "content": "<|video|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

trainer_state.json

@@ -0,0 +1,774 @@
+{
+  "best_global_step": 100,
+  "best_metric": 0.00810375064611435,
+  "best_model_checkpoint": "outputs/gemma-4-31b-it-dft-lora/checkpoint-100",
+  "epoch": 0.02155753166262463,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0002155753166262463,
+      "grad_norm": 0.35355231165885925,
+      "learning_rate": 0.0002,
+      "loss": 0.029262639582157135,
+      "step": 1
+    },
+    {
+      "epoch": 0.0004311506332524926,
+      "grad_norm": 0.8035170435905457,
+      "learning_rate": 0.0002,
+      "loss": 0.034604787826538086,
+      "step": 2
+    },
+    {
+      "epoch": 0.0006467259498787389,
+      "grad_norm": 0.1696992814540863,
+      "learning_rate": 0.0002,
+      "loss": 0.02872493863105774,
+      "step": 3
+    },
+    {
+      "epoch": 0.0008623012665049852,
+      "grad_norm": 0.2127484530210495,
+      "learning_rate": 0.0002,
+      "loss": 0.015632111579179764,
+      "step": 4
+    },
+    {
+      "epoch": 0.0010778765831312314,
+      "grad_norm": 0.08805956691503525,
+      "learning_rate": 0.0002,
+      "loss": 0.01093694195151329,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012934518997574779,
+      "grad_norm": 0.33709272742271423,
+      "learning_rate": 0.0002,
+      "loss": 0.013769567012786865,
+      "step": 6
+    },
+    {
+      "epoch": 0.0015090272163837241,
+      "grad_norm": 1.254341721534729,
+      "learning_rate": 0.0002,
+      "loss": 0.0147835249081254,
+      "step": 7
+    },
+    {
+      "epoch": 0.0017246025330099704,
+      "grad_norm": 0.10053704679012299,
+      "learning_rate": 0.0002,
+      "loss": 0.012731949798762798,
+      "step": 8
+    },
+    {
+      "epoch": 0.0019401778496362166,
+      "grad_norm": 0.12072528898715973,
+      "learning_rate": 0.0002,
+      "loss": 0.010018199682235718,
+      "step": 9
+    },
+    {
+      "epoch": 0.002155753166262463,
+      "grad_norm": 0.14486922323703766,
+      "learning_rate": 0.0002,
+      "loss": 0.011705820448696613,
+      "step": 10
+    },
+    {
+      "epoch": 0.0023713284828887093,
+      "grad_norm": 0.8446067571640015,
+      "learning_rate": 0.0002,
+      "loss": 0.013134717009961605,
+      "step": 11
+    },
+    {
+      "epoch": 0.0025869037995149557,
+      "grad_norm": 0.14635822176933289,
+      "learning_rate": 0.0002,
+      "loss": 0.009777972474694252,
+      "step": 12
+    },
+    {
+      "epoch": 0.0028024791161412018,
+      "grad_norm": 0.3104383945465088,
+      "learning_rate": 0.0002,
+      "loss": 0.008575799874961376,
+      "step": 13
+    },
+    {
+      "epoch": 0.0030180544327674482,
+      "grad_norm": 0.6574239730834961,
+      "learning_rate": 0.0002,
+      "loss": 0.011179640889167786,
+      "step": 14
+    },
+    {
+      "epoch": 0.0032336297493936943,
+      "grad_norm": 0.16107547283172607,
+      "learning_rate": 0.0002,
+      "loss": 0.008740412071347237,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034492050660199407,
+      "grad_norm": 0.1261993795633316,
+      "learning_rate": 0.0002,
+      "loss": 0.009002208709716797,
+      "step": 16
+    },
+    {
+      "epoch": 0.003664780382646187,
+      "grad_norm": 0.11350332945585251,
+      "learning_rate": 0.0002,
+      "loss": 0.012038005515933037,
+      "step": 17
+    },
+    {
+      "epoch": 0.003880355699272433,
+      "grad_norm": 0.1060851514339447,
+      "learning_rate": 0.0002,
+      "loss": 0.01151442900300026,
+      "step": 18
+    },
+    {
+      "epoch": 0.00409593101589868,
+      "grad_norm": 0.14713744819164276,
+      "learning_rate": 0.0002,
+      "loss": 0.009754206985235214,
+      "step": 19
+    },
+    {
+      "epoch": 0.004311506332524926,
+      "grad_norm": 0.16942201554775238,
+      "learning_rate": 0.0002,
+      "loss": 0.009654794819653034,
+      "step": 20
+    },
+    {
+      "epoch": 0.0045270816491511726,
+      "grad_norm": 1.3301082849502563,
+      "learning_rate": 0.0002,
+      "loss": 0.011510669253766537,
+      "step": 21
+    },
+    {
+      "epoch": 0.004742656965777419,
+      "grad_norm": 0.13192863762378693,
+      "learning_rate": 0.0002,
+      "loss": 0.010545970872044563,
+      "step": 22
+    },
+    {
+      "epoch": 0.004958232282403665,
+      "grad_norm": 0.36531829833984375,
+      "learning_rate": 0.0002,
+      "loss": 0.00679993350058794,
+      "step": 23
+    },
+    {
+      "epoch": 0.0051738075990299115,
+      "grad_norm": 0.683217465877533,
+      "learning_rate": 0.0002,
+      "loss": 0.01119004562497139,
+      "step": 24
+    },
+    {
+      "epoch": 0.0053893829156561575,
+      "grad_norm": 0.09257054328918457,
+      "learning_rate": 0.0002,
+      "loss": 0.010483799502253532,
+      "step": 25
+    },
+    {
+      "epoch": 0.0056049582322824035,
+      "grad_norm": 0.38596951961517334,
+      "learning_rate": 0.0002,
+      "loss": 0.007335903123021126,
+      "step": 26
+    },
+    {
+      "epoch": 0.00582053354890865,
+      "grad_norm": 0.10540477186441422,
+      "learning_rate": 0.0002,
+      "loss": 0.008093496784567833,
+      "step": 27
+    },
+    {
+      "epoch": 0.0060361088655348965,
+      "grad_norm": 0.1042870506644249,
+      "learning_rate": 0.0002,
+      "loss": 0.006771376356482506,
+      "step": 28
+    },
+    {
+      "epoch": 0.0062516841821611425,
+      "grad_norm": 0.12241453677415848,
+      "learning_rate": 0.0002,
+      "loss": 0.012486090883612633,
+      "step": 29
+    },
+    {
+      "epoch": 0.0064672594987873885,
+      "grad_norm": 0.07308249920606613,
+      "learning_rate": 0.0002,
+      "loss": 0.008405549451708794,
+      "step": 30
+    },
+    {
+      "epoch": 0.006682834815413635,
+      "grad_norm": 0.5752164125442505,
+      "learning_rate": 0.0002,
+      "loss": 0.00868656300008297,
+      "step": 31
+    },
+    {
+      "epoch": 0.006898410132039881,
+      "grad_norm": 0.440966933965683,
+      "learning_rate": 0.0002,
+      "loss": 0.009276360273361206,
+      "step": 32
+    },
+    {
+      "epoch": 0.0071139854486661274,
+      "grad_norm": 0.10101857036352158,
+      "learning_rate": 0.0002,
+      "loss": 0.009907806292176247,
+      "step": 33
+    },
+    {
+      "epoch": 0.007329560765292374,
+      "grad_norm": 0.10938883572816849,
+      "learning_rate": 0.0002,
+      "loss": 0.010104689747095108,
+      "step": 34
+    },
+    {
+      "epoch": 0.00754513608191862,
+      "grad_norm": 0.10266172885894775,
+      "learning_rate": 0.0002,
+      "loss": 0.01003933884203434,
+      "step": 35
+    },
+    {
+      "epoch": 0.007760711398544866,
+      "grad_norm": 0.6664326190948486,
+      "learning_rate": 0.0002,
+      "loss": 0.008584938943386078,
+      "step": 36
+    },
+    {
+      "epoch": 0.007976286715171112,
+      "grad_norm": 0.12953639030456543,
+      "learning_rate": 0.0002,
+      "loss": 0.010258931666612625,
+      "step": 37
+    },
+    {
+      "epoch": 0.00819186203179736,
+      "grad_norm": 0.1646440178155899,
+      "learning_rate": 0.0002,
+      "loss": 0.007510819472372532,
+      "step": 38
+    },
+    {
+      "epoch": 0.008407437348423606,
+      "grad_norm": 0.1203722283244133,
+      "learning_rate": 0.0002,
+      "loss": 0.008814643137156963,
+      "step": 39
+    },
+    {
+      "epoch": 0.008623012665049851,
+      "grad_norm": 0.2890990376472473,
+      "learning_rate": 0.0002,
+      "loss": 0.00809550192207098,
+      "step": 40
+    },
+    {
+      "epoch": 0.008838587981676098,
+      "grad_norm": 0.08200457692146301,
+      "learning_rate": 0.0002,
+      "loss": 0.009519032202661037,
+      "step": 41
+    },
+    {
+      "epoch": 0.009054163298302345,
+      "grad_norm": 1.1322895288467407,
+      "learning_rate": 0.0002,
+      "loss": 0.009396661072969437,
+      "step": 42
+    },
+    {
+      "epoch": 0.00926973861492859,
+      "grad_norm": 0.18650507926940918,
+      "learning_rate": 0.0002,
+      "loss": 0.00949934870004654,
+      "step": 43
+    },
+    {
+      "epoch": 0.009485313931554837,
+      "grad_norm": 0.0988556295633316,
+      "learning_rate": 0.0002,
+      "loss": 0.011296452954411507,
+      "step": 44
+    },
+    {
+      "epoch": 0.009700889248181084,
+      "grad_norm": 0.1548602432012558,
+      "learning_rate": 0.0002,
+      "loss": 0.007339763920754194,
+      "step": 45
+    },
+    {
+      "epoch": 0.00991646456480733,
+      "grad_norm": 0.12220349907875061,
+      "learning_rate": 0.0002,
+      "loss": 0.009710454382002354,
+      "step": 46
+    },
+    {
+      "epoch": 0.010132039881433576,
+      "grad_norm": 16.374435424804688,
+      "learning_rate": 0.0002,
+      "loss": 0.007745769806206226,
+      "step": 47
+    },
+    {
+      "epoch": 0.010347615198059823,
+      "grad_norm": 0.13246791064739227,
+      "learning_rate": 0.0002,
+      "loss": 0.008885636925697327,
+      "step": 48
+    },
+    {
+      "epoch": 0.010563190514686068,
+      "grad_norm": 0.12659847736358643,
+      "learning_rate": 0.0002,
+      "loss": 0.008172022178769112,
+      "step": 49
+    },
+    {
+      "epoch": 0.010778765831312315,
+      "grad_norm": 1.2109593152999878,
+      "learning_rate": 0.0002,
+      "loss": 0.008851840160787106,
+      "step": 50
+    },
+    {
+      "epoch": 0.01099434114793856,
+      "grad_norm": 2.2849178314208984,
+      "learning_rate": 0.0002,
+      "loss": 0.008759889751672745,
+      "step": 51
+    },
+    {
+      "epoch": 0.011209916464564807,
+      "grad_norm": 0.09035182744264603,
+      "learning_rate": 0.0002,
+      "loss": 0.008502203039824963,
+      "step": 52
+    },
+    {
+      "epoch": 0.011425491781191054,
+      "grad_norm": 1.2929551601409912,
+      "learning_rate": 0.0002,
+      "loss": 0.01136450283229351,
+      "step": 53
+    },
+    {
+      "epoch": 0.0116410670978173,
+      "grad_norm": 0.15647704899311066,
+      "learning_rate": 0.0002,
+      "loss": 0.011929634027183056,
+      "step": 54
+    },
+    {
+      "epoch": 0.011856642414443546,
+      "grad_norm": 0.10196210443973541,
+      "learning_rate": 0.0002,
+      "loss": 0.012628773227334023,
+      "step": 55
+    },
+    {
+      "epoch": 0.012072217731069793,
+      "grad_norm": 0.1851668357849121,
+      "learning_rate": 0.0002,
+      "loss": 0.007304077968001366,
+      "step": 56
+    },
+    {
+      "epoch": 0.012287793047696038,
+      "grad_norm": 0.09506778419017792,
+      "learning_rate": 0.0002,
+      "loss": 0.009885819628834724,
+      "step": 57
+    },
+    {
+      "epoch": 0.012503368364322285,
+      "grad_norm": 1.0429331064224243,
+      "learning_rate": 0.0002,
+      "loss": 0.00825510174036026,
+      "step": 58
+    },
+    {
+      "epoch": 0.012718943680948532,
+      "grad_norm": 0.08919516950845718,
+      "learning_rate": 0.0002,
+      "loss": 0.008733151480555534,
+      "step": 59
+    },
+    {
+      "epoch": 0.012934518997574777,
+      "grad_norm": 0.07233180105686188,
+      "learning_rate": 0.0002,
+      "loss": 0.007502330467104912,
+      "step": 60
+    },
+    {
+      "epoch": 0.013150094314201024,
+      "grad_norm": 0.12755893170833588,
+      "learning_rate": 0.0002,
+      "loss": 0.008441045880317688,
+      "step": 61
+    },
+    {
+      "epoch": 0.01336566963082727,
+      "grad_norm": 0.12750209867954254,
+      "learning_rate": 0.0002,
+      "loss": 0.009924261830747128,
+      "step": 62
+    },
+    {
+      "epoch": 0.013581244947453516,
+      "grad_norm": 0.11990515142679214,
+      "learning_rate": 0.0002,
+      "loss": 0.009097335860133171,
+      "step": 63
+    },
+    {
+      "epoch": 0.013796820264079763,
+      "grad_norm": 0.10748812556266785,
+      "learning_rate": 0.0002,
+      "loss": 0.009064102545380592,
+      "step": 64
+    },
+    {
+      "epoch": 0.01401239558070601,
+      "grad_norm": 0.13909393548965454,
+      "learning_rate": 0.0002,
+      "loss": 0.007015788462013006,
+      "step": 65
+    },
+    {
+      "epoch": 0.014227970897332255,
+      "grad_norm": 0.08622656762599945,
+      "learning_rate": 0.0002,
+      "loss": 0.008788645267486572,
+      "step": 66
+    },
+    {
+      "epoch": 0.014443546213958502,
+      "grad_norm": 0.17846918106079102,
+      "learning_rate": 0.0002,
+      "loss": 0.012987736612558365,
+      "step": 67
+    },
+    {
+      "epoch": 0.014659121530584749,
+      "grad_norm": 0.12868374586105347,
+      "learning_rate": 0.0002,
+      "loss": 0.010869989171624184,
+      "step": 68
+    },
+    {
+      "epoch": 0.014874696847210994,
+      "grad_norm": 0.30010759830474854,
+      "learning_rate": 0.0002,
+      "loss": 0.01126106921583414,
+      "step": 69
+    },
+    {
+      "epoch": 0.01509027216383724,
+      "grad_norm": 0.1034744381904602,
+      "learning_rate": 0.0002,
+      "loss": 0.008966062217950821,
+      "step": 70
+    },
+    {
+      "epoch": 0.015305847480463488,
+      "grad_norm": 0.11833963543176651,
+      "learning_rate": 0.0002,
+      "loss": 0.00806531123816967,
+      "step": 71
+    },
+    {
+      "epoch": 0.015521422797089733,
+      "grad_norm": 0.15848252177238464,
+      "learning_rate": 0.0002,
+      "loss": 0.010981461964547634,
+      "step": 72
+    },
+    {
+      "epoch": 0.01573699811371598,
+      "grad_norm": 0.08389270305633545,
+      "learning_rate": 0.0002,
+      "loss": 0.0057669407688081264,
+      "step": 73
+    },
+    {
+      "epoch": 0.015952573430342225,
+      "grad_norm": 0.0900215208530426,
+      "learning_rate": 0.0002,
+      "loss": 0.008691560477018356,
+      "step": 74
+    },
+    {
+      "epoch": 0.016168148746968473,
+      "grad_norm": 0.17846129834651947,
+      "learning_rate": 0.0002,
+      "loss": 0.009927794337272644,
+      "step": 75
+    },
+    {
+      "epoch": 0.01638372406359472,
+      "grad_norm": 0.10122981667518616,
+      "learning_rate": 0.0002,
+      "loss": 0.00906498171389103,
+      "step": 76
+    },
+    {
+      "epoch": 0.016599299380220964,
+      "grad_norm": 0.14186958968639374,
+      "learning_rate": 0.0002,
+      "loss": 0.008270910941064358,
+      "step": 77
+    },
+    {
+      "epoch": 0.016814874696847212,
+      "grad_norm": 0.11519192904233932,
+      "learning_rate": 0.0002,
+      "loss": 0.006747878156602383,
+      "step": 78
+    },
+    {
+      "epoch": 0.017030450013473458,
+      "grad_norm": 0.16740112006664276,
+      "learning_rate": 0.0002,
+      "loss": 0.009118085727095604,
+      "step": 79
+    },
+    {
+      "epoch": 0.017246025330099703,
+      "grad_norm": 0.11494499444961548,
+      "learning_rate": 0.0002,
+      "loss": 0.009879302233457565,
+      "step": 80
+    },
+    {
+      "epoch": 0.01746160064672595,
+      "grad_norm": 0.09631993621587753,
+      "learning_rate": 0.0002,
+      "loss": 0.010842856019735336,
+      "step": 81
+    },
+    {
+      "epoch": 0.017677175963352196,
+      "grad_norm": 0.13463567197322845,
+      "learning_rate": 0.0002,
+      "loss": 0.008765456266701221,
+      "step": 82
+    },
+    {
+      "epoch": 0.01789275127997844,
+      "grad_norm": 0.13754384219646454,
+      "learning_rate": 0.0002,
+      "loss": 0.009140546433627605,
+      "step": 83
+    },
+    {
+      "epoch": 0.01810832659660469,
+      "grad_norm": 0.13506032526493073,
+      "learning_rate": 0.0002,
+      "loss": 0.009798161685466766,
+      "step": 84
+    },
+    {
+      "epoch": 0.018323901913230935,
+      "grad_norm": 0.13916510343551636,
+      "learning_rate": 0.0002,
+      "loss": 0.008156916126608849,
+      "step": 85
+    },
+    {
+      "epoch": 0.01853947722985718,
+      "grad_norm": 0.16660340130329132,
+      "learning_rate": 0.0002,
+      "loss": 0.008743278682231903,
+      "step": 86
+    },
+    {
+      "epoch": 0.01875505254648343,
+      "grad_norm": 0.10949505120515823,
+      "learning_rate": 0.0002,
+      "loss": 0.010252988897264004,
+      "step": 87
+    },
+    {
+      "epoch": 0.018970627863109674,
+      "grad_norm": 0.08768336474895477,
+      "learning_rate": 0.0002,
+      "loss": 0.007359494920819998,
+      "step": 88
+    },
+    {
+      "epoch": 0.01918620317973592,
+      "grad_norm": 0.09033891558647156,
+      "learning_rate": 0.0002,
+      "loss": 0.007224436849355698,
+      "step": 89
+    },
+    {
+      "epoch": 0.019401778496362168,
+      "grad_norm": 0.09072108566761017,
+      "learning_rate": 0.0002,
+      "loss": 0.007737000472843647,
+      "step": 90
+    },
+    {
+      "epoch": 0.019617353812988413,
+      "grad_norm": 0.10658061504364014,
+      "learning_rate": 0.0002,
+      "loss": 0.007505964487791061,
+      "step": 91
+    },
+    {
+      "epoch": 0.01983292912961466,
+      "grad_norm": 0.1041012704372406,
+      "learning_rate": 0.0002,
+      "loss": 0.009607281535863876,
+      "step": 92
+    },
+    {
+      "epoch": 0.020048504446240907,
+      "grad_norm": 0.12774348258972168,
+      "learning_rate": 0.0002,
+      "loss": 0.011203747242689133,
+      "step": 93
+    },
+    {
+      "epoch": 0.020264079762867152,
+      "grad_norm": 0.09742172807455063,
+      "learning_rate": 0.0002,
+      "loss": 0.007369198836386204,
+      "step": 94
+    },
+    {
+      "epoch": 0.020479655079493397,
+      "grad_norm": 0.20940937101840973,
+      "learning_rate": 0.0002,
+      "loss": 0.0064979312010109425,
+      "step": 95
+    },
+    {
+      "epoch": 0.020695230396119646,
+      "grad_norm": 0.13251495361328125,
+      "learning_rate": 0.0002,
+      "loss": 0.0065713562071323395,
+      "step": 96
+    },
+    {
+      "epoch": 0.02091080571274589,
+      "grad_norm": 0.14764021337032318,
+      "learning_rate": 0.0002,
+      "loss": 0.009372049942612648,
+      "step": 97
+    },
+    {
+      "epoch": 0.021126381029372136,
+      "grad_norm": 0.09942134469747543,
+      "learning_rate": 0.0002,
+      "loss": 0.007254909258335829,
+      "step": 98
+    },
+    {
+      "epoch": 0.02134195634599838,
+      "grad_norm": 0.08200989663600922,
+      "learning_rate": 0.0002,
+      "loss": 0.008239559829235077,
+      "step": 99
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "grad_norm": 0.12532088160514832,
+      "learning_rate": 0.0002,
+      "loss": 0.007804064080119133,
+      "step": 100
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "eval_all_loss": 0.00810375064611435,
+      "eval_all_runtime": 38.3897,
+      "eval_all_samples_per_second": 13.337,
+      "eval_all_steps_per_second": 3.334,
+      "step": 100
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "eval_anchor_loss": 0.004381533712148666,
+      "eval_anchor_runtime": 3.8631,
+      "eval_anchor_samples_per_second": 33.134,
+      "eval_anchor_steps_per_second": 8.283,
+      "step": 100
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "eval_english_chat_loss": 0.008710602298378944,
+      "eval_english_chat_runtime": 23.0788,
+      "eval_english_chat_samples_per_second": 5.546,
+      "eval_english_chat_steps_per_second": 1.387,
+      "step": 100
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "eval_hausa_chat_loss": 0.015651777386665344,
+      "eval_hausa_chat_runtime": 3.9816,
+      "eval_hausa_chat_samples_per_second": 32.147,
+      "eval_hausa_chat_steps_per_second": 8.037,
+      "step": 100
+    },
+    {
+      "epoch": 0.02155753166262463,
+      "eval_tool_loss": 0.003671091515570879,
+      "eval_tool_runtime": 6.7733,
+      "eval_tool_samples_per_second": 18.898,
+      "eval_tool_steps_per_second": 4.724,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4639,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9270422000304128e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b53a79113b09f5824e2f9104d88e0d1b5dbae24b8e93b4865a306c7a6fd1be19
+size 5777