Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,41 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1140/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1145/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1368/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1374/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-14/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1596/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1603/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-175/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1824/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1832/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-21/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-226/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-228/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-229/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-25/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-28/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-339/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-35/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-452/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-456/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-458/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-565/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-678/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-684/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-687/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-791/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-904/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-912/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-916/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: peft
+model_name: functiongemma-270m-ft
+tags:
+- base_model:adapter:google/functiongemma-270m-it
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for functiongemma-270m-ft
+
+This model is a fine-tuned version of [google/functiongemma-270m-it](https://huggingface.co/google/functiongemma-270m-it).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.0
+- TRL: 0.26.2
+- Transformers: 4.57.3
+- Pytorch: 2.9.1+cu126
+- Datasets: 4.4.2
+- Tokenizers: 0.22.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/functiongemma-270m-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": 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 sha256:7928dde199d44046e7339b3180ef9a437769ee30312e96ec6d7698e8c65a9425
+size 15220968

chat_template.jinja

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

checkpoint-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/functiongemma-270m-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 0.18.0

checkpoint-100/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/functiongemma-270m-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b949a2d19013550dc15759a43b82afa580f36a8075a4e927176360b5860014
+size 15220968

checkpoint-100/chat_template.jinja

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

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87add49960e2597b23766d5eaae5110f635f1808951be7a8c52c79581b2ca971
+size 30591307

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62720170a83a3090d54463860fb7e6a5a31ed423be8b00fba65f550854d5f183
+size 14645

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ddf45772e3fdb1efbb8b61b3f29ec8f45379ea9a5bdd8885d9642d597f81f5
+size 1465

checkpoint-100/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sfr_token": "<start_function_response>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899

checkpoint-100/trainer_state.json

@@ -0,0 +1,1034 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.5240228176116943,
+      "epoch": 0.04,
+      "grad_norm": 37.29308319091797,
+      "learning_rate": 2e-05,
+      "loss": 6.9422,
+      "mean_token_accuracy": 0.47347480058670044,
+      "num_tokens": 758.0,
+      "step": 1
+    },
+    {
+      "entropy": 0.5185598134994507,
+      "epoch": 0.08,
+      "grad_norm": 37.85886764526367,
+      "learning_rate": 2e-05,
+      "loss": 6.8565,
+      "mean_token_accuracy": 0.47270306944847107,
+      "num_tokens": 1513.0,
+      "step": 2
+    },
+    {
+      "entropy": 0.5363126993179321,
+      "epoch": 0.12,
+      "grad_norm": 36.92781066894531,
+      "learning_rate": 2e-05,
+      "loss": 6.6136,
+      "mean_token_accuracy": 0.47562581300735474,
+      "num_tokens": 2276.0,
+      "step": 3
+    },
+    {
+      "entropy": 0.5541151762008667,
+      "epoch": 0.16,
+      "grad_norm": 37.46426773071289,
+      "learning_rate": 2e-05,
+      "loss": 6.4114,
+      "mean_token_accuracy": 0.47200000286102295,
+      "num_tokens": 3030.0,
+      "step": 4
+    },
+    {
+      "entropy": 0.6072134375572205,
+      "epoch": 0.2,
+      "grad_norm": 36.258392333984375,
+      "learning_rate": 2e-05,
+      "loss": 5.9563,
+      "mean_token_accuracy": 0.4704301059246063,
+      "num_tokens": 3778.0,
+      "step": 5
+    },
+    {
+      "entropy": 0.6346766948699951,
+      "epoch": 0.24,
+      "grad_norm": 34.2164421081543,
+      "learning_rate": 2e-05,
+      "loss": 5.4104,
+      "mean_token_accuracy": 0.48868176341056824,
+      "num_tokens": 4533.0,
+      "step": 6
+    },
+    {
+      "entropy": 0.699142575263977,
+      "epoch": 0.28,
+      "grad_norm": 31.32328987121582,
+      "learning_rate": 2e-05,
+      "loss": 4.9817,
+      "mean_token_accuracy": 0.48806366324424744,
+      "num_tokens": 5291.0,
+      "step": 7
+    },
+    {
+      "entropy": 0.7639284133911133,
+      "epoch": 0.32,
+      "grad_norm": 27.981550216674805,
+      "learning_rate": 2e-05,
+      "loss": 4.5891,
+      "mean_token_accuracy": 0.5134048461914062,
+      "num_tokens": 6041.0,
+      "step": 8
+    },
+    {
+      "entropy": 0.8184663653373718,
+      "epoch": 0.36,
+      "grad_norm": 23.888887405395508,
+      "learning_rate": 2e-05,
+      "loss": 4.1021,
+      "mean_token_accuracy": 0.535380482673645,
+      "num_tokens": 6794.0,
+      "step": 9
+    },
+    {
+      "entropy": 0.8713943362236023,
+      "epoch": 0.4,
+      "grad_norm": 21.27410125732422,
+      "learning_rate": 2e-05,
+      "loss": 3.863,
+      "mean_token_accuracy": 0.5392809510231018,
+      "num_tokens": 7549.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.9519356489181519,
+      "epoch": 0.44,
+      "grad_norm": 18.26158905029297,
+      "learning_rate": 2e-05,
+      "loss": 3.5874,
+      "mean_token_accuracy": 0.5420560836791992,
+      "num_tokens": 8302.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.025558352470398,
+      "epoch": 0.48,
+      "grad_norm": 16.051610946655273,
+      "learning_rate": 2e-05,
+      "loss": 3.3905,
+      "mean_token_accuracy": 0.5483443737030029,
+      "num_tokens": 9061.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.0597870349884033,
+      "epoch": 0.52,
+      "grad_norm": 13.387225151062012,
+      "learning_rate": 2e-05,
+      "loss": 3.1501,
+      "mean_token_accuracy": 0.5702811479568481,
+      "num_tokens": 9812.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.1256167888641357,
+      "epoch": 0.56,
+      "grad_norm": 11.642187118530273,
+      "learning_rate": 2e-05,
+      "loss": 2.9905,
+      "mean_token_accuracy": 0.5778961181640625,
+      "num_tokens": 10567.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.1595126390457153,
+      "epoch": 0.6,
+      "grad_norm": 10.657787322998047,
+      "learning_rate": 2e-05,
+      "loss": 2.8271,
+      "mean_token_accuracy": 0.5927419066429138,
+      "num_tokens": 11315.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.2265969514846802,
+      "epoch": 0.64,
+      "grad_norm": 9.537993431091309,
+      "learning_rate": 2e-05,
+      "loss": 2.749,
+      "mean_token_accuracy": 0.5964912176132202,
+      "num_tokens": 12060.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.2593307495117188,
+      "epoch": 0.68,
+      "grad_norm": 8.315566062927246,
+      "learning_rate": 2e-05,
+      "loss": 2.5743,
+      "mean_token_accuracy": 0.6169934868812561,
+      "num_tokens": 12829.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.3245295286178589,
+      "epoch": 0.72,
+      "grad_norm": 7.915526390075684,
+      "learning_rate": 2e-05,
+      "loss": 2.5367,
+      "mean_token_accuracy": 0.6194332242012024,
+      "num_tokens": 13574.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.3604302406311035,
+      "epoch": 0.76,
+      "grad_norm": 7.328187942504883,
+      "learning_rate": 2e-05,
+      "loss": 2.4018,
+      "mean_token_accuracy": 0.6255033612251282,
+      "num_tokens": 14323.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.3951760530471802,
+      "epoch": 0.8,
+      "grad_norm": 6.733570098876953,
+      "learning_rate": 2e-05,
+      "loss": 2.317,
+      "mean_token_accuracy": 0.635046124458313,
+      "num_tokens": 15086.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.4354883432388306,
+      "epoch": 0.84,
+      "grad_norm": 6.525688648223877,
+      "learning_rate": 2e-05,
+      "loss": 2.2795,
+      "mean_token_accuracy": 0.6360052824020386,
+      "num_tokens": 15851.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.4653663635253906,
+      "epoch": 0.88,
+      "grad_norm": 6.118790149688721,
+      "learning_rate": 2e-05,
+      "loss": 2.1621,
+      "mean_token_accuracy": 0.6416107416152954,
+      "num_tokens": 16600.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.4949076175689697,
+      "epoch": 0.92,
+      "grad_norm": 5.929473400115967,
+      "learning_rate": 2e-05,
+      "loss": 2.1265,
+      "mean_token_accuracy": 0.6526458859443665,
+      "num_tokens": 17341.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.4969980716705322,
+      "epoch": 0.96,
+      "grad_norm": 5.519643783569336,
+      "learning_rate": 2e-05,
+      "loss": 2.0365,
+      "mean_token_accuracy": 0.6627296805381775,
+      "num_tokens": 18107.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.5308914184570312,
+      "epoch": 1.0,
+      "grad_norm": 5.461964130401611,
+      "learning_rate": 2e-05,
+      "loss": 1.9552,
+      "mean_token_accuracy": 0.6851119995117188,
+      "num_tokens": 18870.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.531392216682434,
+      "epoch": 1.04,
+      "grad_norm": 5.313822269439697,
+      "learning_rate": 2e-05,
+      "loss": 1.8633,
+      "mean_token_accuracy": 0.7098515629768372,
+      "num_tokens": 19615.0,
+      "step": 26
+    },
+    {
+      "entropy": 1.5274267196655273,
+      "epoch": 1.08,
+      "grad_norm": 5.325898170471191,
+      "learning_rate": 2e-05,
+      "loss": 1.9049,
+      "mean_token_accuracy": 0.7068965435028076,
+      "num_tokens": 20373.0,
+      "step": 27
+    },
+    {
+      "entropy": 1.5113599300384521,
+      "epoch": 1.12,
+      "grad_norm": 5.022428512573242,
+      "learning_rate": 2e-05,
+      "loss": 1.7917,
+      "mean_token_accuracy": 0.7334217429161072,
+      "num_tokens": 21131.0,
+      "step": 28
+    },
+    {
+      "entropy": 1.4889423847198486,
+      "epoch": 1.16,
+      "grad_norm": 4.645327568054199,
+      "learning_rate": 2e-05,
+      "loss": 1.7032,
+      "mean_token_accuracy": 0.7447090148925781,
+      "num_tokens": 21891.0,
+      "step": 29
+    },
+    {
+      "entropy": 1.4870576858520508,
+      "epoch": 1.2,
+      "grad_norm": 4.541719913482666,
+      "learning_rate": 2e-05,
+      "loss": 1.6655,
+      "mean_token_accuracy": 0.7360000014305115,
+      "num_tokens": 22645.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.4613386392593384,
+      "epoch": 1.24,
+      "grad_norm": 4.408016204833984,
+      "learning_rate": 2e-05,
+      "loss": 1.6312,
+      "mean_token_accuracy": 0.7432795763015747,
+      "num_tokens": 23393.0,
+      "step": 31
+    },
+    {
+      "entropy": 1.4358580112457275,
+      "epoch": 1.28,
+      "grad_norm": 4.297278881072998,
+      "learning_rate": 2e-05,
+      "loss": 1.5793,
+      "mean_token_accuracy": 0.7510094046592712,
+      "num_tokens": 24140.0,
+      "step": 32
+    },
+    {
+      "entropy": 1.3814220428466797,
+      "epoch": 1.32,
+      "grad_norm": 4.178844451904297,
+      "learning_rate": 2e-05,
+      "loss": 1.4675,
+      "mean_token_accuracy": 0.7724867463111877,
+      "num_tokens": 24900.0,
+      "step": 33
+    },
+    {
+      "entropy": 1.3687061071395874,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 4.218804836273193,
+      "learning_rate": 2e-05,
+      "loss": 1.4288,
+      "mean_token_accuracy": 0.7776280045509338,
+      "num_tokens": 25646.0,
+      "step": 34
+    },
+    {
+      "entropy": 1.3419899940490723,
+      "epoch": 1.4,
+      "grad_norm": 4.205630302429199,
+      "learning_rate": 2e-05,
+      "loss": 1.4188,
+      "mean_token_accuracy": 0.7807486653327942,
+      "num_tokens": 26398.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.2921583652496338,
+      "epoch": 1.44,
+      "grad_norm": 3.8976969718933105,
+      "learning_rate": 2e-05,
+      "loss": 1.3454,
+      "mean_token_accuracy": 0.7848605513572693,
+      "num_tokens": 27155.0,
+      "step": 36
+    },
+    {
+      "entropy": 1.2668341398239136,
+      "epoch": 1.48,
+      "grad_norm": 3.746513843536377,
+      "learning_rate": 2e-05,
+      "loss": 1.3557,
+      "mean_token_accuracy": 0.7797062993049622,
+      "num_tokens": 27908.0,
+      "step": 37
+    },
+    {
+      "entropy": 1.228274941444397,
+      "epoch": 1.52,
+      "grad_norm": 3.520526170730591,
+      "learning_rate": 2e-05,
+      "loss": 1.2668,
+      "mean_token_accuracy": 0.8029294013977051,
+      "num_tokens": 28663.0,
+      "step": 38
+    },
+    {
+      "entropy": 1.1697431802749634,
+      "epoch": 1.56,
+      "grad_norm": 3.4416074752807617,
+      "learning_rate": 2e-05,
+      "loss": 1.1742,
+      "mean_token_accuracy": 0.8176870942115784,
+      "num_tokens": 29402.0,
+      "step": 39
+    },
+    {
+      "entropy": 1.130076289176941,
+      "epoch": 1.6,
+      "grad_norm": 3.223904848098755,
+      "learning_rate": 2e-05,
+      "loss": 1.1646,
+      "mean_token_accuracy": 0.8208168745040894,
+      "num_tokens": 30165.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.1070514917373657,
+      "epoch": 1.6400000000000001,
+      "grad_norm": 3.213395118713379,
+      "learning_rate": 2e-05,
+      "loss": 1.1102,
+      "mean_token_accuracy": 0.8348745107650757,
+      "num_tokens": 30926.0,
+      "step": 41
+    },
+    {
+      "entropy": 1.0644617080688477,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 3.1568286418914795,
+      "learning_rate": 2e-05,
+      "loss": 1.0741,
+      "mean_token_accuracy": 0.8320000171661377,
+      "num_tokens": 31680.0,
+      "step": 42
+    },
+    {
+      "entropy": 1.031175971031189,
+      "epoch": 1.72,
+      "grad_norm": 3.1758995056152344,
+      "learning_rate": 2e-05,
+      "loss": 1.0527,
+      "mean_token_accuracy": 0.8251001238822937,
+      "num_tokens": 32433.0,
+      "step": 43
+    },
+    {
+      "entropy": 0.9702178835868835,
+      "epoch": 1.76,
+      "grad_norm": 3.0158236026763916,
+      "learning_rate": 2e-05,
+      "loss": 0.9569,
+      "mean_token_accuracy": 0.8379814028739929,
+      "num_tokens": 33190.0,
+      "step": 44
+    },
+    {
+      "entropy": 0.9418991208076477,
+      "epoch": 1.8,
+      "grad_norm": 3.095254898071289,
+      "learning_rate": 2e-05,
+      "loss": 0.9229,
+      "mean_token_accuracy": 0.852150559425354,
+      "num_tokens": 33938.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.8792616128921509,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 3.1904547214508057,
+      "learning_rate": 2e-05,
+      "loss": 0.8814,
+      "mean_token_accuracy": 0.8521400690078735,
+      "num_tokens": 34713.0,
+      "step": 46
+    },
+    {
+      "entropy": 0.8644114136695862,
+      "epoch": 1.88,
+      "grad_norm": 3.1296632289886475,
+      "learning_rate": 2e-05,
+      "loss": 0.9185,
+      "mean_token_accuracy": 0.8663967847824097,
+      "num_tokens": 35458.0,
+      "step": 47
+    },
+    {
+      "entropy": 0.8369636535644531,
+      "epoch": 1.92,
+      "grad_norm": 3.080310106277466,
+      "learning_rate": 2e-05,
+      "loss": 0.8598,
+      "mean_token_accuracy": 0.875,
+      "num_tokens": 36214.0,
+      "step": 48
+    },
+    {
+      "entropy": 0.7779583930969238,
+      "epoch": 1.96,
+      "grad_norm": 2.9825854301452637,
+      "learning_rate": 2e-05,
+      "loss": 0.757,
+      "mean_token_accuracy": 0.8845144510269165,
+      "num_tokens": 36980.0,
+      "step": 49
+    },
+    {
+      "entropy": 0.7366280555725098,
+      "epoch": 2.0,
+      "grad_norm": 3.0169920921325684,
+      "learning_rate": 2e-05,
+      "loss": 0.7402,
+      "mean_token_accuracy": 0.8928571343421936,
+      "num_tokens": 37740.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.7010611891746521,
+      "epoch": 2.04,
+      "grad_norm": 3.399986743927002,
+      "learning_rate": 2e-05,
+      "loss": 0.7593,
+      "mean_token_accuracy": 0.8872870206832886,
+      "num_tokens": 38507.0,
+      "step": 51
+    },
+    {
+      "entropy": 0.6273115873336792,
+      "epoch": 2.08,
+      "grad_norm": 3.619697332382202,
+      "learning_rate": 2e-05,
+      "loss": 0.6621,
+      "mean_token_accuracy": 0.9089692234992981,
+      "num_tokens": 39258.0,
+      "step": 52
+    },
+    {
+      "entropy": 0.5995044708251953,
+      "epoch": 2.12,
+      "grad_norm": 2.8443078994750977,
+      "learning_rate": 2e-05,
+      "loss": 0.662,
+      "mean_token_accuracy": 0.9167767763137817,
+      "num_tokens": 40019.0,
+      "step": 53
+    },
+    {
+      "entropy": 0.5483225584030151,
+      "epoch": 2.16,
+      "grad_norm": 2.8451199531555176,
+      "learning_rate": 2e-05,
+      "loss": 0.575,
+      "mean_token_accuracy": 0.929427444934845,
+      "num_tokens": 40774.0,
+      "step": 54
+    },
+    {
+      "entropy": 0.5085722208023071,
+      "epoch": 2.2,
+      "grad_norm": 2.7123143672943115,
+      "learning_rate": 2e-05,
+      "loss": 0.5672,
+      "mean_token_accuracy": 0.9348404407501221,
+      "num_tokens": 41530.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.4458790123462677,
+      "epoch": 2.24,
+      "grad_norm": 2.668097496032715,
+      "learning_rate": 2e-05,
+      "loss": 0.5034,
+      "mean_token_accuracy": 0.9419702887535095,
+      "num_tokens": 42275.0,
+      "step": 56
+    },
+    {
+      "entropy": 0.3930673599243164,
+      "epoch": 2.2800000000000002,
+      "grad_norm": 2.5482311248779297,
+      "learning_rate": 2e-05,
+      "loss": 0.5078,
+      "mean_token_accuracy": 0.9355263113975525,
+      "num_tokens": 43039.0,
+      "step": 57
+    },
+    {
+      "entropy": 0.37228837609291077,
+      "epoch": 2.32,
+      "grad_norm": 2.443922281265259,
+      "learning_rate": 2e-05,
+      "loss": 0.4665,
+      "mean_token_accuracy": 0.9482071995735168,
+      "num_tokens": 43796.0,
+      "step": 58
+    },
+    {
+      "entropy": 0.3517550826072693,
+      "epoch": 2.36,
+      "grad_norm": 2.3463053703308105,
+      "learning_rate": 2e-05,
+      "loss": 0.4632,
+      "mean_token_accuracy": 0.9378378391265869,
+      "num_tokens": 44540.0,
+      "step": 59
+    },
+    {
+      "entropy": 0.33203697204589844,
+      "epoch": 2.4,
+      "grad_norm": 2.6731350421905518,
+      "learning_rate": 2e-05,
+      "loss": 0.4491,
+      "mean_token_accuracy": 0.9372549057006836,
+      "num_tokens": 45309.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.31520795822143555,
+      "epoch": 2.44,
+      "grad_norm": 2.3959364891052246,
+      "learning_rate": 2e-05,
+      "loss": 0.44,
+      "mean_token_accuracy": 0.9494680762290955,
+      "num_tokens": 46065.0,
+      "step": 61
+    },
+    {
+      "entropy": 0.3004280626773834,
+      "epoch": 2.48,
+      "grad_norm": 2.1749024391174316,
+      "learning_rate": 2e-05,
+      "loss": 0.4511,
+      "mean_token_accuracy": 0.9522546529769897,
+      "num_tokens": 46823.0,
+      "step": 62
+    },
+    {
+      "entropy": 0.287904292345047,
+      "epoch": 2.52,
+      "grad_norm": 2.184871196746826,
+      "learning_rate": 2e-05,
+      "loss": 0.4058,
+      "mean_token_accuracy": 0.9521276354789734,
+      "num_tokens": 47579.0,
+      "step": 63
+    },
+    {
+      "entropy": 0.28218233585357666,
+      "epoch": 2.56,
+      "grad_norm": 2.27091121673584,
+      "learning_rate": 2e-05,
+      "loss": 0.3679,
+      "mean_token_accuracy": 0.9529569745063782,
+      "num_tokens": 48327.0,
+      "step": 64
+    },
+    {
+      "entropy": 0.2818812429904938,
+      "epoch": 2.6,
+      "grad_norm": 2.9275169372558594,
+      "learning_rate": 2e-05,
+      "loss": 0.3858,
+      "mean_token_accuracy": 0.9478609561920166,
+      "num_tokens": 49079.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.2774568200111389,
+      "epoch": 2.64,
+      "grad_norm": 2.837167978286743,
+      "learning_rate": 2e-05,
+      "loss": 0.3639,
+      "mean_token_accuracy": 0.9430463314056396,
+      "num_tokens": 49838.0,
+      "step": 66
+    },
+    {
+      "entropy": 0.2726022005081177,
+      "epoch": 2.68,
+      "grad_norm": 2.2975914478302,
+      "learning_rate": 2e-05,
+      "loss": 0.3028,
+      "mean_token_accuracy": 0.9518072009086609,
+      "num_tokens": 50589.0,
+      "step": 67
+    },
+    {
+      "entropy": 0.25494953989982605,
+      "epoch": 2.7199999999999998,
+      "grad_norm": 2.0497214794158936,
+      "learning_rate": 2e-05,
+      "loss": 0.2769,
+      "mean_token_accuracy": 0.9570469856262207,
+      "num_tokens": 51338.0,
+      "step": 68
+    },
+    {
+      "entropy": 0.2599942982196808,
+      "epoch": 2.76,
+      "grad_norm": 2.4737048149108887,
+      "learning_rate": 2e-05,
+      "loss": 0.336,
+      "mean_token_accuracy": 0.9518072009086609,
+      "num_tokens": 52089.0,
+      "step": 69
+    },
+    {
+      "entropy": 0.24719160795211792,
+      "epoch": 2.8,
+      "grad_norm": 2.1889803409576416,
+      "learning_rate": 2e-05,
+      "loss": 0.3006,
+      "mean_token_accuracy": 0.9491298794746399,
+      "num_tokens": 52840.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.24826745688915253,
+      "epoch": 2.84,
+      "grad_norm": 2.0455644130706787,
+      "learning_rate": 2e-05,
+      "loss": 0.2918,
+      "mean_token_accuracy": 0.948344349861145,
+      "num_tokens": 53599.0,
+      "step": 71
+    },
+    {
+      "entropy": 0.2431359887123108,
+      "epoch": 2.88,
+      "grad_norm": 1.8650648593902588,
+      "learning_rate": 2e-05,
+      "loss": 0.2582,
+      "mean_token_accuracy": 0.9523809552192688,
+      "num_tokens": 54359.0,
+      "step": 72
+    },
+    {
+      "entropy": 0.24409686028957367,
+      "epoch": 2.92,
+      "grad_norm": 2.3259599208831787,
+      "learning_rate": 2e-05,
+      "loss": 0.2527,
+      "mean_token_accuracy": 0.960106372833252,
+      "num_tokens": 55115.0,
+      "step": 73
+    },
+    {
+      "entropy": 0.2385331094264984,
+      "epoch": 2.96,
+      "grad_norm": 1.3533285856246948,
+      "learning_rate": 2e-05,
+      "loss": 0.2706,
+      "mean_token_accuracy": 0.9580514430999756,
+      "num_tokens": 55858.0,
+      "step": 74
+    },
+    {
+      "entropy": 0.24642708897590637,
+      "epoch": 3.0,
+      "grad_norm": 1.1475350856781006,
+      "learning_rate": 2e-05,
+      "loss": 0.2543,
+      "mean_token_accuracy": 0.9598930478096008,
+      "num_tokens": 56610.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.2539970278739929,
+      "epoch": 3.04,
+      "grad_norm": 1.2767738103866577,
+      "learning_rate": 2e-05,
+      "loss": 0.2488,
+      "mean_token_accuracy": 0.959785521030426,
+      "num_tokens": 57360.0,
+      "step": 76
+    },
+    {
+      "entropy": 0.23603883385658264,
+      "epoch": 3.08,
+      "grad_norm": 1.0374062061309814,
+      "learning_rate": 2e-05,
+      "loss": 0.2453,
+      "mean_token_accuracy": 0.9582772254943848,
+      "num_tokens": 58107.0,
+      "step": 77
+    },
+    {
+      "entropy": 0.24485909938812256,
+      "epoch": 3.12,
+      "grad_norm": 1.4987839460372925,
+      "learning_rate": 2e-05,
+      "loss": 0.2312,
+      "mean_token_accuracy": 0.9553219676017761,
+      "num_tokens": 58872.0,
+      "step": 78
+    },
+    {
+      "entropy": 0.2403731644153595,
+      "epoch": 3.16,
+      "grad_norm": 1.1765466928482056,
+      "learning_rate": 2e-05,
+      "loss": 0.2526,
+      "mean_token_accuracy": 0.9653333425521851,
+      "num_tokens": 59626.0,
+      "step": 79
+    },
+    {
+      "entropy": 0.23074936866760254,
+      "epoch": 3.2,
+      "grad_norm": 1.2395281791687012,
+      "learning_rate": 2e-05,
+      "loss": 0.2189,
+      "mean_token_accuracy": 0.9634641408920288,
+      "num_tokens": 60369.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.2089882791042328,
+      "epoch": 3.24,
+      "grad_norm": 1.3069368600845337,
+      "learning_rate": 2e-05,
+      "loss": 0.2428,
+      "mean_token_accuracy": 0.9638069868087769,
+      "num_tokens": 61119.0,
+      "step": 81
+    },
+    {
+      "entropy": 0.21510061621665955,
+      "epoch": 3.2800000000000002,
+      "grad_norm": 1.1535745859146118,
+      "learning_rate": 2e-05,
+      "loss": 0.2212,
+      "mean_token_accuracy": 0.9652870297431946,
+      "num_tokens": 61872.0,
+      "step": 82
+    },
+    {
+      "entropy": 0.2101171612739563,
+      "epoch": 3.32,
+      "grad_norm": 0.9777595400810242,
+      "learning_rate": 2e-05,
+      "loss": 0.1982,
+      "mean_token_accuracy": 0.9693741798400879,
+      "num_tokens": 62627.0,
+      "step": 83
+    },
+    {
+      "entropy": 0.2099580019712448,
+      "epoch": 3.36,
+      "grad_norm": 1.1317825317382812,
+      "learning_rate": 2e-05,
+      "loss": 0.2281,
+      "mean_token_accuracy": 0.9669312238693237,
+      "num_tokens": 63387.0,
+      "step": 84
+    },
+    {
+      "entropy": 0.20581887662410736,
+      "epoch": 3.4,
+      "grad_norm": 1.0572807788848877,
+      "learning_rate": 2e-05,
+      "loss": 0.2033,
+      "mean_token_accuracy": 0.9680851101875305,
+      "num_tokens": 64143.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.20909777283668518,
+      "epoch": 3.44,
+      "grad_norm": 1.5825022459030151,
+      "learning_rate": 2e-05,
+      "loss": 0.2105,
+      "mean_token_accuracy": 0.9637096524238586,
+      "num_tokens": 64891.0,
+      "step": 86
+    },
+    {
+      "entropy": 0.21373741328716278,
+      "epoch": 3.48,
+      "grad_norm": 1.1368229389190674,
+      "learning_rate": 2e-05,
+      "loss": 0.1793,
+      "mean_token_accuracy": 0.9785522818565369,
+      "num_tokens": 65641.0,
+      "step": 87
+    },
+    {
+      "entropy": 0.20942555367946625,
+      "epoch": 3.52,
+      "grad_norm": 1.03619384765625,
+      "learning_rate": 2e-05,
+      "loss": 0.2048,
+      "mean_token_accuracy": 0.9744966626167297,
+      "num_tokens": 66390.0,
+      "step": 88
+    },
+    {
+      "entropy": 0.20285017788410187,
+      "epoch": 3.56,
+      "grad_norm": 0.9636878371238708,
+      "learning_rate": 2e-05,
+      "loss": 0.1875,
+      "mean_token_accuracy": 0.9801587462425232,
+      "num_tokens": 67150.0,
+      "step": 89
+    },
+    {
+      "entropy": 0.20965717732906342,
+      "epoch": 3.6,
+      "grad_norm": 0.782873809337616,
+      "learning_rate": 2e-05,
+      "loss": 0.1866,
+      "mean_token_accuracy": 0.9747676253318787,
+      "num_tokens": 67907.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.17947089672088623,
+      "epoch": 3.64,
+      "grad_norm": 1.3582860231399536,
+      "learning_rate": 2e-05,
+      "loss": 0.1939,
+      "mean_token_accuracy": 0.9734395742416382,
+      "num_tokens": 68664.0,
+      "step": 91
+    },
+    {
+      "entropy": 0.21160392463207245,
+      "epoch": 3.68,
+      "grad_norm": 1.0390849113464355,
+      "learning_rate": 2e-05,
+      "loss": 0.1893,
+      "mean_token_accuracy": 0.9735449552536011,
+      "num_tokens": 69424.0,
+      "step": 92
+    },
+    {
+      "entropy": 0.20336918532848358,
+      "epoch": 3.7199999999999998,
+      "grad_norm": 1.523485541343689,
+      "learning_rate": 2e-05,
+      "loss": 0.2236,
+      "mean_token_accuracy": 0.9635416865348816,
+      "num_tokens": 70196.0,
+      "step": 93
+    },
+    {
+      "entropy": 0.19648239016532898,
+      "epoch": 3.76,
+      "grad_norm": 1.1465239524841309,
+      "learning_rate": 2e-05,
+      "loss": 0.243,
+      "mean_token_accuracy": 0.9677852392196655,
+      "num_tokens": 70945.0,
+      "step": 94
+    },
+    {
+      "entropy": 0.16573190689086914,
+      "epoch": 3.8,
+      "grad_norm": 0.9433248043060303,
+      "learning_rate": 2e-05,
+      "loss": 0.1588,
+      "mean_token_accuracy": 0.9879999756813049,
+      "num_tokens": 71699.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.1826864331960678,
+      "epoch": 3.84,
+      "grad_norm": 0.8109387159347534,
+      "learning_rate": 2e-05,
+      "loss": 0.1688,
+      "mean_token_accuracy": 0.9801061153411865,
+      "num_tokens": 72457.0,
+      "step": 96
+    },
+    {
+      "entropy": 0.16375097632408142,
+      "epoch": 3.88,
+      "grad_norm": 0.7381296753883362,
+      "learning_rate": 2e-05,
+      "loss": 0.1766,
+      "mean_token_accuracy": 0.9775132536888123,
+      "num_tokens": 73217.0,
+      "step": 97
+    },
+    {
+      "entropy": 0.1716109961271286,
+      "epoch": 3.92,
+      "grad_norm": 0.8144583106040955,
+      "learning_rate": 2e-05,
+      "loss": 0.1895,
+      "mean_token_accuracy": 0.9759358167648315,
+      "num_tokens": 73969.0,
+      "step": 98
+    },
+    {
+      "entropy": 0.1795879453420639,
+      "epoch": 3.96,
+      "grad_norm": 0.7693735957145691,
+      "learning_rate": 2e-05,
+      "loss": 0.1644,
+      "mean_token_accuracy": 0.9772727489471436,
+      "num_tokens": 74721.0,
+      "step": 99
+    },
+    {
+      "entropy": 0.17074991762638092,
+      "epoch": 4.0,
+      "grad_norm": 1.033590316772461,
+      "learning_rate": 2e-05,
+      "loss": 0.1741,
+      "mean_token_accuracy": 0.9721854329109192,
+      "num_tokens": 75480.0,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 48089835982848.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bbbac5dfa7eeab06b7825aa1cc5d579813c31431cabeb7c04e2aa72c4d6d43
+size 6225

checkpoint-113/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/functiongemma-270m-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 0.18.0

checkpoint-113/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/functiongemma-270m-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-113/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb1de17c52355c955619f8214957c44e37674ce2c6389e7fd30fac3786727f38
+size 15220968

checkpoint-113/chat_template.jinja

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

checkpoint-113/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3512092b47e632fcc3216ef3f04dea5e65a9d5399823144dc2a3d4342059c58
+size 30591307

checkpoint-113/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252b3a5c29ee54d6cd2781df7604615003f94498c291144c67de0ff7b662b797
+size 14645

checkpoint-113/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255d2eceb5f4ca3dd5a4e23b16aa987d8fa640658efdb995fdcc0d9d3c820ce0
+size 1465

checkpoint-113/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sfr_token": "<start_function_response>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-113/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899

checkpoint-113/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.3933267489075661,
+      "epoch": 0.08888888888888889,
+      "grad_norm": 19.091772079467773,
+      "learning_rate": 2e-05,
+      "loss": 4.2829,
+      "mean_token_accuracy": 0.5681655570864678,
+      "num_tokens": 29409.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.7650148034095764,
+      "epoch": 0.17777777777777778,
+      "grad_norm": 3.8214948177337646,
+      "learning_rate": 2e-05,
+      "loss": 1.9461,
+      "mean_token_accuracy": 0.6879387736320496,
+      "num_tokens": 58827.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.1828202903270721,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 2.6364810466766357,
+      "learning_rate": 2e-05,
+      "loss": 1.4227,
+      "mean_token_accuracy": 0.7338245347142219,
+      "num_tokens": 88299.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.134617891907692,
+      "epoch": 0.35555555555555557,
+      "grad_norm": 1.9795665740966797,
+      "learning_rate": 2e-05,
+      "loss": 1.1307,
+      "mean_token_accuracy": 0.7887017637491226,
+      "num_tokens": 117759.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.877768449485302,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 1.8397494554519653,
+      "learning_rate": 2e-05,
+      "loss": 0.8535,
+      "mean_token_accuracy": 0.8351033940911293,
+      "num_tokens": 147140.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.587233804166317,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.7626832723617554,
+      "learning_rate": 2e-05,
+      "loss": 0.5781,
+      "mean_token_accuracy": 0.8860435307025909,
+      "num_tokens": 176659.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.3405880033969879,
+      "epoch": 0.6222222222222222,
+      "grad_norm": 1.520534634590149,
+      "learning_rate": 2e-05,
+      "loss": 0.3419,
+      "mean_token_accuracy": 0.9315642505884171,
+      "num_tokens": 206147.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.19235755391418935,
+      "epoch": 0.7111111111111111,
+      "grad_norm": 1.268977403640747,
+      "learning_rate": 2e-05,
+      "loss": 0.1858,
+      "mean_token_accuracy": 0.9728681713342666,
+      "num_tokens": 235603.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.11804858762770891,
+      "epoch": 0.8,
+      "grad_norm": 0.781975269317627,
+      "learning_rate": 2e-05,
+      "loss": 0.1064,
+      "mean_token_accuracy": 0.9887924045324326,
+      "num_tokens": 265047.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.09983876422047615,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.4874080419540405,
+      "learning_rate": 2e-05,
+      "loss": 0.0815,
+      "mean_token_accuracy": 0.9895498856902123,
+      "num_tokens": 294524.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.08479245882481337,
+      "epoch": 0.9777777777777777,
+      "grad_norm": 0.3734425902366638,
+      "learning_rate": 2e-05,
+      "loss": 0.0768,
+      "mean_token_accuracy": 0.9904760375618935,
+      "num_tokens": 324032.0,
+      "step": 110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 904,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 207041312797440.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-113/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993cb24984dd499229bfa88ab126ff39685a1cf19c7cf87786770b5bf8e8e018
+size 6225

checkpoint-1140/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/functiongemma-270m-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 0.18.0

checkpoint-1140/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/functiongemma-270m-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1140/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37024e0032ed8d70e8ecc9c6d85512df11b15ee98850e26e807c4bcb64aa14cd
+size 15220968

checkpoint-1140/chat_template.jinja

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

checkpoint-1140/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72ae6fb2b95a28e0e510fcb4391873d20fa5568f10674aa8fc2a949992446ad
+size 30591307

checkpoint-1140/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1dda932f8114abaee571282d7023c06cdb61d148796a106ed6ea7c1a4b3cba
+size 14645

checkpoint-1140/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec860d5213feb1c1f9493d3582479f18e0ad80779b7de6dcdbec577e011f836
+size 1465

checkpoint-1140/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sfr_token": "<start_function_response>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1140/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899

checkpoint-1140/trainer_state.json

@@ -0,0 +1,1174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.3891168855130672,
+      "epoch": 0.043859649122807015,
+      "grad_norm": 18.536834716796875,
+      "learning_rate": 2e-05,
+      "loss": 4.281,
+      "mean_token_accuracy": 0.5703265547752381,
+      "num_tokens": 29513.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.749189381301403,
+      "epoch": 0.08771929824561403,
+      "grad_norm": 3.8398051261901855,
+      "learning_rate": 2e-05,
+      "loss": 1.9625,
+      "mean_token_accuracy": 0.6897866070270539,
+      "num_tokens": 58932.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.169826951622963,
+      "epoch": 0.13157894736842105,
+      "grad_norm": 2.5061917304992676,
+      "learning_rate": 2e-05,
+      "loss": 1.4255,
+      "mean_token_accuracy": 0.7357227891683579,
+      "num_tokens": 88352.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.1334790736436844,
+      "epoch": 0.17543859649122806,
+      "grad_norm": 1.9473565816879272,
+      "learning_rate": 2e-05,
+      "loss": 1.1315,
+      "mean_token_accuracy": 0.7862708762288093,
+      "num_tokens": 117877.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8736076682806015,
+      "epoch": 0.21929824561403508,
+      "grad_norm": 1.7826578617095947,
+      "learning_rate": 2e-05,
+      "loss": 0.8549,
+      "mean_token_accuracy": 0.8343304082751274,
+      "num_tokens": 147392.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.5955807730555535,
+      "epoch": 0.2631578947368421,
+      "grad_norm": 1.6632131338119507,
+      "learning_rate": 2e-05,
+      "loss": 0.58,
+      "mean_token_accuracy": 0.8876266479492188,
+      "num_tokens": 176728.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.34382262006402015,
+      "epoch": 0.30701754385964913,
+      "grad_norm": 1.4843252897262573,
+      "learning_rate": 2e-05,
+      "loss": 0.3445,
+      "mean_token_accuracy": 0.9318736225366593,
+      "num_tokens": 206184.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.19373956136405468,
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.904003918170929,
+      "learning_rate": 2e-05,
+      "loss": 0.189,
+      "mean_token_accuracy": 0.9710342198610306,
+      "num_tokens": 235688.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.12052652426064014,
+      "epoch": 0.39473684210526316,
+      "grad_norm": 0.7406700849533081,
+      "learning_rate": 2e-05,
+      "loss": 0.1056,
+      "mean_token_accuracy": 0.9886028110980988,
+      "num_tokens": 265172.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.0992697212845087,
+      "epoch": 0.43859649122807015,
+      "grad_norm": 0.606019139289856,
+      "learning_rate": 2e-05,
+      "loss": 0.0817,
+      "mean_token_accuracy": 0.989163076877594,
+      "num_tokens": 294687.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.08367474023252726,
+      "epoch": 0.4824561403508772,
+      "grad_norm": 0.4705955386161804,
+      "learning_rate": 2e-05,
+      "loss": 0.0737,
+      "mean_token_accuracy": 0.9905414953827858,
+      "num_tokens": 324088.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.07386345528066159,
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.4300910234451294,
+      "learning_rate": 2e-05,
+      "loss": 0.0631,
+      "mean_token_accuracy": 0.9910139158368111,
+      "num_tokens": 353582.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.06888655042275786,
+      "epoch": 0.5701754385964912,
+      "grad_norm": 0.45082923769950867,
+      "learning_rate": 2e-05,
+      "loss": 0.0661,
+      "mean_token_accuracy": 0.9910464301705361,
+      "num_tokens": 383080.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.06553246006369591,
+      "epoch": 0.6140350877192983,
+      "grad_norm": 0.4258216619491577,
+      "learning_rate": 2e-05,
+      "loss": 0.0615,
+      "mean_token_accuracy": 0.9914803236722947,
+      "num_tokens": 412559.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.06352790119126439,
+      "epoch": 0.6578947368421053,
+      "grad_norm": 0.37360644340515137,
+      "learning_rate": 2e-05,
+      "loss": 0.0579,
+      "mean_token_accuracy": 0.9916400715708733,
+      "num_tokens": 442008.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.060972847137600185,
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.3406882584095001,
+      "learning_rate": 2e-05,
+      "loss": 0.0576,
+      "mean_token_accuracy": 0.9914845108985901,
+      "num_tokens": 471495.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.05891128294169903,
+      "epoch": 0.7456140350877193,
+      "grad_norm": 0.2854160964488983,
+      "learning_rate": 2e-05,
+      "loss": 0.057,
+      "mean_token_accuracy": 0.9915445119142532,
+      "num_tokens": 500954.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.0579888011328876,
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.40168505907058716,
+      "learning_rate": 2e-05,
+      "loss": 0.0507,
+      "mean_token_accuracy": 0.9923512250185013,
+      "num_tokens": 530401.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.0573225624859333,
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.4589792490005493,
+      "learning_rate": 2e-05,
+      "loss": 0.0561,
+      "mean_token_accuracy": 0.9916056364774704,
+      "num_tokens": 559940.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.05970530286431312,
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.5275149941444397,
+      "learning_rate": 2e-05,
+      "loss": 0.0573,
+      "mean_token_accuracy": 0.9915869951248169,
+      "num_tokens": 589427.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.059507152158766986,
+      "epoch": 0.9210526315789473,
+      "grad_norm": 0.2661688029766083,
+      "learning_rate": 2e-05,
+      "loss": 0.0515,
+      "mean_token_accuracy": 0.9923170626163482,
+      "num_tokens": 618838.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.05687206219881773,
+      "epoch": 0.9649122807017544,
+      "grad_norm": 0.35179731249809265,
+      "learning_rate": 2e-05,
+      "loss": 0.0506,
+      "mean_token_accuracy": 0.9918064430356026,
+      "num_tokens": 648258.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.058181710354983804,
+      "epoch": 1.0087719298245614,
+      "grad_norm": 0.3514145314693451,
+      "learning_rate": 2e-05,
+      "loss": 0.0522,
+      "mean_token_accuracy": 0.9915239199995994,
+      "num_tokens": 677779.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.055358363036066296,
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.3630446493625641,
+      "learning_rate": 2e-05,
+      "loss": 0.0482,
+      "mean_token_accuracy": 0.9922210231423378,
+      "num_tokens": 707217.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.0538893367163837,
+      "epoch": 1.0964912280701755,
+      "grad_norm": 0.3740084767341614,
+      "learning_rate": 2e-05,
+      "loss": 0.0448,
+      "mean_token_accuracy": 0.9927210569381714,
+      "num_tokens": 736641.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.0544189871288836,
+      "epoch": 1.1403508771929824,
+      "grad_norm": 0.31057634949684143,
+      "learning_rate": 2e-05,
+      "loss": 0.0474,
+      "mean_token_accuracy": 0.9922840282320976,
+      "num_tokens": 766189.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.053078283276408914,
+      "epoch": 1.1842105263157894,
+      "grad_norm": 0.21449895203113556,
+      "learning_rate": 2e-05,
+      "loss": 0.0468,
+      "mean_token_accuracy": 0.9923206493258476,
+      "num_tokens": 795639.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.05415161233395338,
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.30692726373672485,
+      "learning_rate": 2e-05,
+      "loss": 0.0458,
+      "mean_token_accuracy": 0.9922255620360374,
+      "num_tokens": 825119.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.05160839455202222,
+      "epoch": 1.2719298245614035,
+      "grad_norm": 0.3166206479072571,
+      "learning_rate": 2e-05,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9921553313732148,
+      "num_tokens": 854581.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.05075615206733346,
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.3627457618713379,
+      "learning_rate": 2e-05,
+      "loss": 0.0417,
+      "mean_token_accuracy": 0.9924884453415871,
+      "num_tokens": 884020.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.0517747713252902,
+      "epoch": 1.3596491228070176,
+      "grad_norm": 0.37561649084091187,
+      "learning_rate": 2e-05,
+      "loss": 0.0435,
+      "mean_token_accuracy": 0.992647610604763,
+      "num_tokens": 913529.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.05250948471948504,
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.42561790347099304,
+      "learning_rate": 2e-05,
+      "loss": 0.0431,
+      "mean_token_accuracy": 0.9922929123044014,
+      "num_tokens": 942986.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.05172846736386418,
+      "epoch": 1.4473684210526316,
+      "grad_norm": 0.2577071785926819,
+      "learning_rate": 2e-05,
+      "loss": 0.041,
+      "mean_token_accuracy": 0.9923748031258584,
+      "num_tokens": 972495.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.04749757144600153,
+      "epoch": 1.4912280701754386,
+      "grad_norm": 0.25072360038757324,
+      "learning_rate": 2e-05,
+      "loss": 0.0402,
+      "mean_token_accuracy": 0.9924940422177315,
+      "num_tokens": 1001947.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.04762007407844067,
+      "epoch": 1.5350877192982457,
+      "grad_norm": 0.3604894280433655,
+      "learning_rate": 2e-05,
+      "loss": 0.0392,
+      "mean_token_accuracy": 0.992351396381855,
+      "num_tokens": 1031488.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.047403684537857774,
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.2911185920238495,
+      "learning_rate": 2e-05,
+      "loss": 0.0381,
+      "mean_token_accuracy": 0.9927886813879013,
+      "num_tokens": 1060887.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.04852928835898638,
+      "epoch": 1.6228070175438596,
+      "grad_norm": 0.2618354856967926,
+      "learning_rate": 2e-05,
+      "loss": 0.0385,
+      "mean_token_accuracy": 0.9927341029047966,
+      "num_tokens": 1090348.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.04723916696384549,
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.26962020993232727,
+      "learning_rate": 2e-05,
+      "loss": 0.0383,
+      "mean_token_accuracy": 0.9925345599651336,
+      "num_tokens": 1119839.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.046288730949163436,
+      "epoch": 1.7105263157894737,
+      "grad_norm": 0.4525667130947113,
+      "learning_rate": 2e-05,
+      "loss": 0.0352,
+      "mean_token_accuracy": 0.9927756577730179,
+      "num_tokens": 1149317.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.04401880670338869,
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.23167090117931366,
+      "learning_rate": 2e-05,
+      "loss": 0.0354,
+      "mean_token_accuracy": 0.9926382765173912,
+      "num_tokens": 1178783.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.04442735444754362,
+      "epoch": 1.7982456140350878,
+      "grad_norm": 0.2764274477958679,
+      "learning_rate": 2e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9925318494439125,
+      "num_tokens": 1208255.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.046166476979851725,
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.3111913800239563,
+      "learning_rate": 2e-05,
+      "loss": 0.0385,
+      "mean_token_accuracy": 0.992423489689827,
+      "num_tokens": 1237708.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.044908494455739856,
+      "epoch": 1.8859649122807016,
+      "grad_norm": 0.23237602412700653,
+      "learning_rate": 2e-05,
+      "loss": 0.0385,
+      "mean_token_accuracy": 0.9935551881790161,
+      "num_tokens": 1267186.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.04562048772349954,
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.25153592228889465,
+      "learning_rate": 2e-05,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9941498264670372,
+      "num_tokens": 1296591.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.044570739334449175,
+      "epoch": 1.973684210526316,
+      "grad_norm": 0.23802141845226288,
+      "learning_rate": 2e-05,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9942585557699204,
+      "num_tokens": 1326042.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.044205385353416206,
+      "epoch": 2.017543859649123,
+      "grad_norm": 0.3467763066291809,
+      "learning_rate": 2e-05,
+      "loss": 0.0331,
+      "mean_token_accuracy": 0.9940735891461372,
+      "num_tokens": 1355561.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.042760218819603325,
+      "epoch": 2.06140350877193,
+      "grad_norm": 0.2680515646934509,
+      "learning_rate": 2e-05,
+      "loss": 0.0319,
+      "mean_token_accuracy": 0.9945705458521843,
+      "num_tokens": 1385048.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.04117725370451808,
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.39523598551750183,
+      "learning_rate": 2e-05,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9936558306217194,
+      "num_tokens": 1414543.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.04356150296516716,
+      "epoch": 2.1491228070175437,
+      "grad_norm": 0.23617857694625854,
+      "learning_rate": 2e-05,
+      "loss": 0.0332,
+      "mean_token_accuracy": 0.9941312283277511,
+      "num_tokens": 1444017.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.04058904880657792,
+      "epoch": 2.192982456140351,
+      "grad_norm": 0.3990024924278259,
+      "learning_rate": 2e-05,
+      "loss": 0.0285,
+      "mean_token_accuracy": 0.9948335066437721,
+      "num_tokens": 1473442.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.04089017482474446,
+      "epoch": 2.236842105263158,
+      "grad_norm": 0.22417540848255157,
+      "learning_rate": 2e-05,
+      "loss": 0.0314,
+      "mean_token_accuracy": 0.994497561454773,
+      "num_tokens": 1502879.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.04202216519042849,
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.20546036958694458,
+      "learning_rate": 2e-05,
+      "loss": 0.0321,
+      "mean_token_accuracy": 0.9938287988305092,
+      "num_tokens": 1532392.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.04143659081310034,
+      "epoch": 2.324561403508772,
+      "grad_norm": 0.26604264974594116,
+      "learning_rate": 2e-05,
+      "loss": 0.0313,
+      "mean_token_accuracy": 0.9944339916110039,
+      "num_tokens": 1561839.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.03936287453398109,
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.23989664018154144,
+      "learning_rate": 2e-05,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.9943608403205871,
+      "num_tokens": 1591271.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.039195985486730936,
+      "epoch": 2.412280701754386,
+      "grad_norm": 0.3053726255893707,
+      "learning_rate": 2e-05,
+      "loss": 0.0306,
+      "mean_token_accuracy": 0.9943523585796357,
+      "num_tokens": 1620794.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.039683265471830965,
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.2588869631290436,
+      "learning_rate": 2e-05,
+      "loss": 0.0293,
+      "mean_token_accuracy": 0.9944723203778267,
+      "num_tokens": 1650276.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.03602620945312083,
+      "epoch": 2.5,
+      "grad_norm": 0.2668582797050476,
+      "learning_rate": 2e-05,
+      "loss": 0.0292,
+      "mean_token_accuracy": 0.9945638462901115,
+      "num_tokens": 1679717.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.03886530273593962,
+      "epoch": 2.543859649122807,
+      "grad_norm": 0.2594759464263916,
+      "learning_rate": 2e-05,
+      "loss": 0.0294,
+      "mean_token_accuracy": 0.9944349855184555,
+      "num_tokens": 1709202.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.03563018930144608,
+      "epoch": 2.587719298245614,
+      "grad_norm": 0.22012071311473846,
+      "learning_rate": 2e-05,
+      "loss": 0.0272,
+      "mean_token_accuracy": 0.9947109371423721,
+      "num_tokens": 1738701.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.03517519012093544,
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.2758197486400604,
+      "learning_rate": 2e-05,
+      "loss": 0.03,
+      "mean_token_accuracy": 0.9942290917038917,
+      "num_tokens": 1768151.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.03706208867952228,
+      "epoch": 2.675438596491228,
+      "grad_norm": 0.3245140016078949,
+      "learning_rate": 2e-05,
+      "loss": 0.0288,
+      "mean_token_accuracy": 0.9942933633923531,
+      "num_tokens": 1797583.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.034479991812258956,
+      "epoch": 2.719298245614035,
+      "grad_norm": 0.22120347619056702,
+      "learning_rate": 2e-05,
+      "loss": 0.0282,
+      "mean_token_accuracy": 0.9947970882058144,
+      "num_tokens": 1827006.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.033304579788818955,
+      "epoch": 2.763157894736842,
+      "grad_norm": 0.26880016922950745,
+      "learning_rate": 2e-05,
+      "loss": 0.0277,
+      "mean_token_accuracy": 0.994759914278984,
+      "num_tokens": 1856428.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.0331753586884588,
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.24720199406147003,
+      "learning_rate": 2e-05,
+      "loss": 0.0278,
+      "mean_token_accuracy": 0.9946068048477172,
+      "num_tokens": 1885916.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.03345069149509072,
+      "epoch": 2.8508771929824563,
+      "grad_norm": 0.27891653776168823,
+      "learning_rate": 2e-05,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9948126003146172,
+      "num_tokens": 1915396.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.0333542559761554,
+      "epoch": 2.8947368421052633,
+      "grad_norm": 0.4004022479057312,
+      "learning_rate": 2e-05,
+      "loss": 0.0289,
+      "mean_token_accuracy": 0.9938531696796418,
+      "num_tokens": 1945009.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.02968177660368383,
+      "epoch": 2.93859649122807,
+      "grad_norm": 0.2902744710445404,
+      "learning_rate": 2e-05,
+      "loss": 0.0241,
+      "mean_token_accuracy": 0.9945998504757881,
+      "num_tokens": 1974462.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.0323303550016135,
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.2170533686876297,
+      "learning_rate": 2e-05,
+      "loss": 0.0287,
+      "mean_token_accuracy": 0.9943123281002044,
+      "num_tokens": 2003840.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.0318671815097332,
+      "epoch": 3.026315789473684,
+      "grad_norm": 0.19683605432510376,
+      "learning_rate": 2e-05,
+      "loss": 0.027,
+      "mean_token_accuracy": 0.9946763277053833,
+      "num_tokens": 2033324.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.03094636939931661,
+      "epoch": 3.0701754385964914,
+      "grad_norm": 0.3156299889087677,
+      "learning_rate": 2e-05,
+      "loss": 0.027,
+      "mean_token_accuracy": 0.9943998187780381,
+      "num_tokens": 2062796.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.029998012352734804,
+      "epoch": 3.1140350877192984,
+      "grad_norm": 0.19611181318759918,
+      "learning_rate": 2e-05,
+      "loss": 0.0251,
+      "mean_token_accuracy": 0.9945186242461205,
+      "num_tokens": 2092349.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.02844015813898295,
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.3108363151550293,
+      "learning_rate": 2e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9948573753237724,
+      "num_tokens": 2121717.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.02917947373352945,
+      "epoch": 3.2017543859649122,
+      "grad_norm": 0.3223120868206024,
+      "learning_rate": 2e-05,
+      "loss": 0.0259,
+      "mean_token_accuracy": 0.9950737491250038,
+      "num_tokens": 2151171.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.02822321942076087,
+      "epoch": 3.245614035087719,
+      "grad_norm": 0.1794469654560089,
+      "learning_rate": 2e-05,
+      "loss": 0.0258,
+      "mean_token_accuracy": 0.9945150166749954,
+      "num_tokens": 2180705.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.026581059489399195,
+      "epoch": 3.2894736842105265,
+      "grad_norm": 0.2445470094680786,
+      "learning_rate": 2e-05,
+      "loss": 0.026,
+      "mean_token_accuracy": 0.9945855379104614,
+      "num_tokens": 2210233.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.02701793306041509,
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.28041425347328186,
+      "learning_rate": 2e-05,
+      "loss": 0.0237,
+      "mean_token_accuracy": 0.9952751606702804,
+      "num_tokens": 2239637.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.03019589218311012,
+      "epoch": 3.3771929824561404,
+      "grad_norm": 0.25402745604515076,
+      "learning_rate": 2e-05,
+      "loss": 0.0283,
+      "mean_token_accuracy": 0.9943036273121834,
+      "num_tokens": 2269135.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.030228979233652354,
+      "epoch": 3.4210526315789473,
+      "grad_norm": 0.22020572423934937,
+      "learning_rate": 2e-05,
+      "loss": 0.0269,
+      "mean_token_accuracy": 0.9944290310144425,
+      "num_tokens": 2298575.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.03184722135774791,
+      "epoch": 3.4649122807017543,
+      "grad_norm": 0.2342633605003357,
+      "learning_rate": 2e-05,
+      "loss": 0.0263,
+      "mean_token_accuracy": 0.9947415545582772,
+      "num_tokens": 2328042.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.02975663202814758,
+      "epoch": 3.5087719298245617,
+      "grad_norm": 0.46808409690856934,
+      "learning_rate": 2e-05,
+      "loss": 0.0277,
+      "mean_token_accuracy": 0.9943336308002472,
+      "num_tokens": 2357539.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.02755520197097212,
+      "epoch": 3.5526315789473686,
+      "grad_norm": 0.2859908938407898,
+      "learning_rate": 2e-05,
+      "loss": 0.0269,
+      "mean_token_accuracy": 0.9948696240782737,
+      "num_tokens": 2386963.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.0279413893353194,
+      "epoch": 3.5964912280701755,
+      "grad_norm": 0.2786264419555664,
+      "learning_rate": 2e-05,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9943128302693367,
+      "num_tokens": 2416501.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.02768249998334795,
+      "epoch": 3.6403508771929824,
+      "grad_norm": 0.22936373949050903,
+      "learning_rate": 2e-05,
+      "loss": 0.0239,
+      "mean_token_accuracy": 0.9947321966290474,
+      "num_tokens": 2445941.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.02423749384470284,
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.2773398756980896,
+      "learning_rate": 2e-05,
+      "loss": 0.0225,
+      "mean_token_accuracy": 0.9952654018998146,
+      "num_tokens": 2475299.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.02699003741145134,
+      "epoch": 3.7280701754385968,
+      "grad_norm": 0.23085203766822815,
+      "learning_rate": 2e-05,
+      "loss": 0.0257,
+      "mean_token_accuracy": 0.9947722434997559,
+      "num_tokens": 2504764.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.029456905997358264,
+      "epoch": 3.7719298245614032,
+      "grad_norm": 0.2776418924331665,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9948301285505294,
+      "num_tokens": 2534185.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.026715041836723685,
+      "epoch": 3.8157894736842106,
+      "grad_norm": 0.40782320499420166,
+      "learning_rate": 2e-05,
+      "loss": 0.0263,
+      "mean_token_accuracy": 0.9943931043148041,
+      "num_tokens": 2563632.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.026448413264006376,
+      "epoch": 3.8596491228070176,
+      "grad_norm": 0.20839615166187286,
+      "learning_rate": 2e-05,
+      "loss": 0.0253,
+      "mean_token_accuracy": 0.9949382901191711,
+      "num_tokens": 2593079.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.026889733923599123,
+      "epoch": 3.9035087719298245,
+      "grad_norm": 0.4022772014141083,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9950519934296608,
+      "num_tokens": 2622599.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.02558579680044204,
+      "epoch": 3.9473684210526314,
+      "grad_norm": 0.23025710880756378,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9947320595383644,
+      "num_tokens": 2652027.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.026929323840886355,
+      "epoch": 3.9912280701754383,
+      "grad_norm": 0.558501660823822,
+      "learning_rate": 2e-05,
+      "loss": 0.0263,
+      "mean_token_accuracy": 0.9945844635367393,
+      "num_tokens": 2681568.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.027245206129737198,
+      "epoch": 4.035087719298246,
+      "grad_norm": 0.34754958748817444,
+      "learning_rate": 2e-05,
+      "loss": 0.0267,
+      "mean_token_accuracy": 0.9946398049592972,
+      "num_tokens": 2711021.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.028458662680350244,
+      "epoch": 4.078947368421052,
+      "grad_norm": 0.2995450496673584,
+      "learning_rate": 2e-05,
+      "loss": 0.027,
+      "mean_token_accuracy": 0.994346709549427,
+      "num_tokens": 2740564.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.026019252184778453,
+      "epoch": 4.12280701754386,
+      "grad_norm": 0.18306803703308105,
+      "learning_rate": 2e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.995404352247715,
+      "num_tokens": 2769966.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.025571403023786844,
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.24489884078502655,
+      "learning_rate": 2e-05,
+      "loss": 0.0227,
+      "mean_token_accuracy": 0.99520303606987,
+      "num_tokens": 2799356.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.02373389925342053,
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.4220126271247864,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.994646181166172,
+      "num_tokens": 2828878.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.02672711748164147,
+      "epoch": 4.254385964912281,
+      "grad_norm": 0.20107538998126984,
+      "learning_rate": 2e-05,
+      "loss": 0.0233,
+      "mean_token_accuracy": 0.9949999019503594,
+      "num_tokens": 2858288.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.02580628953874111,
+      "epoch": 4.298245614035087,
+      "grad_norm": 0.3406866490840912,
+      "learning_rate": 2e-05,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9947706565260888,
+      "num_tokens": 2887762.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.02430701975245029,
+      "epoch": 4.342105263157895,
+      "grad_norm": 0.28178682923316956,
+      "learning_rate": 2e-05,
+      "loss": 0.0229,
+      "mean_token_accuracy": 0.9950452461838722,
+      "num_tokens": 2917219.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.026894421339966355,
+      "epoch": 4.385964912280702,
+      "grad_norm": 0.28810808062553406,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.994709712266922,
+      "num_tokens": 2946727.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.026626669918186963,
+      "epoch": 4.4298245614035086,
+      "grad_norm": 0.2008417248725891,
+      "learning_rate": 2e-05,
+      "loss": 0.0247,
+      "mean_token_accuracy": 0.9952127397060394,
+      "num_tokens": 2976166.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.02615027381107211,
+      "epoch": 4.473684210526316,
+      "grad_norm": 0.3345981240272522,
+      "learning_rate": 2e-05,
+      "loss": 0.0229,
+      "mean_token_accuracy": 0.9947855144739151,
+      "num_tokens": 3005701.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.02315097493119538,
+      "epoch": 4.517543859649123,
+      "grad_norm": 0.2304411679506302,
+      "learning_rate": 2e-05,
+      "loss": 0.023,
+      "mean_token_accuracy": 0.9950236231088638,
+      "num_tokens": 3035228.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.024475370533764362,
+      "epoch": 4.56140350877193,
+      "grad_norm": 0.2187710851430893,
+      "learning_rate": 2e-05,
+      "loss": 0.0237,
+      "mean_token_accuracy": 0.994983771443367,
+      "num_tokens": 3064721.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.024467523396015167,
+      "epoch": 4.605263157894737,
+      "grad_norm": 0.2989374101161957,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.994673240184784,
+      "num_tokens": 3094215.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.02632226881105453,
+      "epoch": 4.649122807017544,
+      "grad_norm": 0.33434978127479553,
+      "learning_rate": 2e-05,
+      "loss": 0.0234,
+      "mean_token_accuracy": 0.9951106742024421,
+      "num_tokens": 3123674.0,
+      "step": 1060
+    },
+    {
+      "entropy": 0.025994484080001712,
+      "epoch": 4.692982456140351,
+      "grad_norm": 0.3363839089870453,
+      "learning_rate": 2e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9950530841946602,
+      "num_tokens": 3153200.0,
+      "step": 1070
+    },
+    {
+      "entropy": 0.024378301412798464,
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.27308163046836853,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.9951689943671227,
+      "num_tokens": 3182589.0,
+      "step": 1080
+    },
+    {
+      "entropy": 0.02580142463557422,
+      "epoch": 4.780701754385965,
+      "grad_norm": 0.3396266996860504,
+      "learning_rate": 2e-05,
+      "loss": 0.0225,
+      "mean_token_accuracy": 0.9950757563114166,
+      "num_tokens": 3212040.0,
+      "step": 1090
+    },
+    {
+      "entropy": 0.024319417704828084,
+      "epoch": 4.824561403508772,
+      "grad_norm": 0.23770387470722198,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.9949398577213288,
+      "num_tokens": 3241483.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.024646017188206314,
+      "epoch": 4.868421052631579,
+      "grad_norm": 0.18578499555587769,
+      "learning_rate": 2e-05,
+      "loss": 0.0216,
+      "mean_token_accuracy": 0.995578208565712,
+      "num_tokens": 3270879.0,
+      "step": 1110
+    },
+    {
+      "entropy": 0.025846811849623917,
+      "epoch": 4.912280701754386,
+      "grad_norm": 0.2943616509437561,
+      "learning_rate": 2e-05,
+      "loss": 0.0262,
+      "mean_token_accuracy": 0.9946421980857849,
+      "num_tokens": 3300390.0,
+      "step": 1120
+    },
+    {
+      "entropy": 0.02559350139927119,
+      "epoch": 4.956140350877193,
+      "grad_norm": 0.3006184995174408,
+      "learning_rate": 2e-05,
+      "loss": 0.0246,
+      "mean_token_accuracy": 0.9950146496295929,
+      "num_tokens": 3329878.0,
+      "step": 1130
+    },
+    {
+      "entropy": 0.027681316062808037,
+      "epoch": 5.0,
+      "grad_norm": 0.2197951078414917,
+      "learning_rate": 2e-05,
+      "loss": 0.0255,
+      "mean_token_accuracy": 0.9948058515787125,
+      "num_tokens": 3359340.0,
+      "step": 1140
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1824,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2098707514168320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1140/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6625b0622d8188e768d0234598af3bece8f3ddac5e738886f92637144f417b4c
+size 6225

checkpoint-1145/README.md

@@ -0,0 +1,209 @@
+---
+base_model: google/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:google/functiongemma-270m-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 0.18.0

checkpoint-1145/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/functiongemma-270m-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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1145/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bd38458a01840de9d233724738125d6b58f3a2c517a838430e30f4706a635c
+size 15220968

checkpoint-1145/chat_template.jinja

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

checkpoint-1145/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff66b874e2c66ea0b03a7a7ef4352f056f2b9b68633de3819aa538168859a059
+size 30591307

checkpoint-1145/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1464181e26bf58297268494110c256952741ab48b7f7c871fc103b5142f2a7ee
+size 14645

checkpoint-1145/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be855bce872bc70bd40eccb7ee250665fa8589ecfda29c45f01c53498d866b70
+size 1465

checkpoint-1145/special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sfr_token": "<start_function_response>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1145/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6b09a0b4a803ad453063ca4bb49a784540e8120004e2450e025df2b27d41fb2
+size 33384899