Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,63 @@ 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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5725/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-700/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,9 +1,207 @@
 ---
-license: apache-2.0
-datasets:
-- AnishJoshi/nl2bash-custom
-language:
-- en
-base_model:
-- google/functiongemma-270m-it
----
+base_model: unsloth/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/functiongemma-270m-it
+- lora
+- transformers
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/functiongemma-270m-it",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_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:a2cf492613544bc73d1dae992745252f8a44cfa4a6bd5389d2ab4849336ed8aa
+size 60785144

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end_of_image>": 262145,
+  "<image_soft_token>": 262144
+}

chat_template.jinja

@@ -0,0 +1,282 @@
+{%- 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:] -%}
+    {%- else -%}
+        {{- 'You are a model that can do function calling with the following functions' -}}
+        {%- set loop_messages = messages -%}
+    {%- 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 +1,207 @@
+---
+base_model: unsloth/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/functiongemma-270m-it
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/functiongemma-270m-it",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_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:b41ff92fff37b5682d4b5f3367e2231e5fd6183251401b9206874b535cd02de7
+size 60785144

checkpoint-100/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end_of_image>": 262145,
+  "<image_soft_token>": 262144
+}

checkpoint-100/chat_template.jinja

@@ -0,0 +1,282 @@
+{%- 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:] -%}
+    {%- else -%}
+        {{- 'You are a model that can do function calling with the following functions' -}}
+        {%- set loop_messages = messages -%}
+    {%- 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 sha256:356da361c0a6d635b5d9c3aa1b51d9790c3a346c7730a5d0ca962946d04ea8ff
+size 121708939

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb03eac9b58e52273c3aa5727841719fd6c82afc9062bbaf8eb6f842de779278
+size 14391

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5862e5e0650ed902623f865842c02c99e7054853606c904f823dfbad3f1915b
+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": "<end_of_turn>",
+    "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/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
+size 4689144

checkpoint-100/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08737439930100481,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00436871996505024,
+      "grad_norm": 9.839941024780273,
+      "learning_rate": 8e-05,
+      "loss": 2.5246,
+      "step": 5
+    },
+    {
+      "epoch": 0.00873743993010048,
+      "grad_norm": 13.773455619812012,
+      "learning_rate": 0.00018,
+      "loss": 1.1343,
+      "step": 10
+    },
+    {
+      "epoch": 0.01310615989515072,
+      "grad_norm": 5.6580424308776855,
+      "learning_rate": 0.0001999997582552296,
+      "loss": 0.7712,
+      "step": 15
+    },
+    {
+      "epoch": 0.01747487986020096,
+      "grad_norm": 5.294467926025391,
+      "learning_rate": 0.0001999987761691029,
+      "loss": 0.73,
+      "step": 20
+    },
+    {
+      "epoch": 0.021843599825251202,
+      "grad_norm": 2.8633503913879395,
+      "learning_rate": 0.00019999703863998527,
+      "loss": 0.7289,
+      "step": 25
+    },
+    {
+      "epoch": 0.02621231979030144,
+      "grad_norm": 3.2836177349090576,
+      "learning_rate": 0.00019999454568100293,
+      "loss": 0.4686,
+      "step": 30
+    },
+    {
+      "epoch": 0.03058103975535168,
+      "grad_norm": 4.878258228302002,
+      "learning_rate": 0.00019999129731098898,
+      "loss": 0.6629,
+      "step": 35
+    },
+    {
+      "epoch": 0.03494975972040192,
+      "grad_norm": 2.899914026260376,
+      "learning_rate": 0.00019998729355448326,
+      "loss": 0.6038,
+      "step": 40
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 3.289844274520874,
+      "learning_rate": 0.00019998253444173235,
+      "loss": 0.4573,
+      "step": 45
+    },
+    {
+      "epoch": 0.043687199650502405,
+      "grad_norm": 2.957254648208618,
+      "learning_rate": 0.00019997702000868896,
+      "loss": 0.594,
+      "step": 50
+    },
+    {
+      "epoch": 0.048055919615552646,
+      "grad_norm": 3.171276807785034,
+      "learning_rate": 0.00019997075029701207,
+      "loss": 0.5719,
+      "step": 55
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 2.55605149269104,
+      "learning_rate": 0.0001999637253540663,
+      "loss": 0.5971,
+      "step": 60
+    },
+    {
+      "epoch": 0.05679335954565312,
+      "grad_norm": 2.127289295196533,
+      "learning_rate": 0.00019995594523292178,
+      "loss": 0.5712,
+      "step": 65
+    },
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 3.3928685188293457,
+      "learning_rate": 0.00019994740999235359,
+      "loss": 0.5712,
+      "step": 70
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 2.6700279712677,
+      "learning_rate": 0.00019993811969684142,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "epoch": 0.06989951944080385,
+      "grad_norm": 2.6936633586883545,
+      "learning_rate": 0.00019992807441656898,
+      "loss": 0.5321,
+      "step": 80
+    },
+    {
+      "epoch": 0.07426823940585409,
+      "grad_norm": 3.9897687435150146,
+      "learning_rate": 0.00019991727422742362,
+      "loss": 0.6025,
+      "step": 85
+    },
+    {
+      "epoch": 0.07863695937090433,
+      "grad_norm": 2.3496663570404053,
+      "learning_rate": 0.00019990571921099553,
+      "loss": 0.5975,
+      "step": 90
+    },
+    {
+      "epoch": 0.08300567933595457,
+      "grad_norm": 3.3796467781066895,
+      "learning_rate": 0.0001998934094545774,
+      "loss": 0.5255,
+      "step": 95
+    },
+    {
+      "epoch": 0.08737439930100481,
+      "grad_norm": 3.1103007793426514,
+      "learning_rate": 0.00019988034505116352,
+      "loss": 0.4946,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5725,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 48194282348544.0,
+  "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 sha256:629a35960f565450f5c9e65334fb9c14eb136182b8af4bc22c885bdde32de5f3
+size 5777

checkpoint-1000/README.md

@@ -0,0 +1,207 @@
+---
+base_model: unsloth/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/functiongemma-270m-it
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/functiongemma-270m-it",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:133ec76379027ec222f56f4cc1b04ae3342877261ab6c165c6b4fd334e8022bb
+size 60785144

checkpoint-1000/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end_of_image>": 262145,
+  "<image_soft_token>": 262144
+}

checkpoint-1000/chat_template.jinja

@@ -0,0 +1,282 @@
+{%- 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:] -%}
+    {%- else -%}
+        {{- 'You are a model that can do function calling with the following functions' -}}
+        {%- set loop_messages = messages -%}
+    {%- 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-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc305b4ad5727d63269f4d0392a3c827627bff7f82346016ac21b101c20d0e6f
+size 121708939

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb03eac9b58e52273c3aa5727841719fd6c82afc9062bbaf8eb6f842de779278
+size 14391

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d07d0c8b6dccd1d2b3163f43a15635d0989081116d1ae61ad5b1d2af1ac480
+size 1465

checkpoint-1000/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": "<end_of_turn>",
+    "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-1000/tokenizer.json

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

checkpoint-1000/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
+size 4689144

checkpoint-1000/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.873743993010048,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00436871996505024,
+      "grad_norm": 9.839941024780273,
+      "learning_rate": 8e-05,
+      "loss": 2.5246,
+      "step": 5
+    },
+    {
+      "epoch": 0.00873743993010048,
+      "grad_norm": 13.773455619812012,
+      "learning_rate": 0.00018,
+      "loss": 1.1343,
+      "step": 10
+    },
+    {
+      "epoch": 0.01310615989515072,
+      "grad_norm": 5.6580424308776855,
+      "learning_rate": 0.0001999997582552296,
+      "loss": 0.7712,
+      "step": 15
+    },
+    {
+      "epoch": 0.01747487986020096,
+      "grad_norm": 5.294467926025391,
+      "learning_rate": 0.0001999987761691029,
+      "loss": 0.73,
+      "step": 20
+    },
+    {
+      "epoch": 0.021843599825251202,
+      "grad_norm": 2.8633503913879395,
+      "learning_rate": 0.00019999703863998527,
+      "loss": 0.7289,
+      "step": 25
+    },
+    {
+      "epoch": 0.02621231979030144,
+      "grad_norm": 3.2836177349090576,
+      "learning_rate": 0.00019999454568100293,
+      "loss": 0.4686,
+      "step": 30
+    },
+    {
+      "epoch": 0.03058103975535168,
+      "grad_norm": 4.878258228302002,
+      "learning_rate": 0.00019999129731098898,
+      "loss": 0.6629,
+      "step": 35
+    },
+    {
+      "epoch": 0.03494975972040192,
+      "grad_norm": 2.899914026260376,
+      "learning_rate": 0.00019998729355448326,
+      "loss": 0.6038,
+      "step": 40
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 3.289844274520874,
+      "learning_rate": 0.00019998253444173235,
+      "loss": 0.4573,
+      "step": 45
+    },
+    {
+      "epoch": 0.043687199650502405,
+      "grad_norm": 2.957254648208618,
+      "learning_rate": 0.00019997702000868896,
+      "loss": 0.594,
+      "step": 50
+    },
+    {
+      "epoch": 0.048055919615552646,
+      "grad_norm": 3.171276807785034,
+      "learning_rate": 0.00019997075029701207,
+      "loss": 0.5719,
+      "step": 55
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 2.55605149269104,
+      "learning_rate": 0.0001999637253540663,
+      "loss": 0.5971,
+      "step": 60
+    },
+    {
+      "epoch": 0.05679335954565312,
+      "grad_norm": 2.127289295196533,
+      "learning_rate": 0.00019995594523292178,
+      "loss": 0.5712,
+      "step": 65
+    },
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 3.3928685188293457,
+      "learning_rate": 0.00019994740999235359,
+      "loss": 0.5712,
+      "step": 70
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 2.6700279712677,
+      "learning_rate": 0.00019993811969684142,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "epoch": 0.06989951944080385,
+      "grad_norm": 2.6936633586883545,
+      "learning_rate": 0.00019992807441656898,
+      "loss": 0.5321,
+      "step": 80
+    },
+    {
+      "epoch": 0.07426823940585409,
+      "grad_norm": 3.9897687435150146,
+      "learning_rate": 0.00019991727422742362,
+      "loss": 0.6025,
+      "step": 85
+    },
+    {
+      "epoch": 0.07863695937090433,
+      "grad_norm": 2.3496663570404053,
+      "learning_rate": 0.00019990571921099553,
+      "loss": 0.5975,
+      "step": 90
+    },
+    {
+      "epoch": 0.08300567933595457,
+      "grad_norm": 3.3796467781066895,
+      "learning_rate": 0.0001998934094545774,
+      "loss": 0.5255,
+      "step": 95
+    },
+    {
+      "epoch": 0.08737439930100481,
+      "grad_norm": 3.1103007793426514,
+      "learning_rate": 0.00019988034505116352,
+      "loss": 0.4946,
+      "step": 100
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 2.002304792404175,
+      "learning_rate": 0.00019986652609944926,
+      "loss": 0.425,
+      "step": 105
+    },
+    {
+      "epoch": 0.09611183923110529,
+      "grad_norm": 1.7572168111801147,
+      "learning_rate": 0.00019985195270383018,
+      "loss": 0.6073,
+      "step": 110
+    },
+    {
+      "epoch": 0.10048055919615553,
+      "grad_norm": 2.745215654373169,
+      "learning_rate": 0.00019983662497440133,
+      "loss": 0.586,
+      "step": 115
+    },
+    {
+      "epoch": 0.10484927916120576,
+      "grad_norm": 1.8170915842056274,
+      "learning_rate": 0.0001998205430269564,
+      "loss": 0.5255,
+      "step": 120
+    },
+    {
+      "epoch": 0.109217999126256,
+      "grad_norm": 1.4944056272506714,
+      "learning_rate": 0.00019980370698298677,
+      "loss": 0.4219,
+      "step": 125
+    },
+    {
+      "epoch": 0.11358671909130624,
+      "grad_norm": 1.6616989374160767,
+      "learning_rate": 0.00019978611696968074,
+      "loss": 0.4231,
+      "step": 130
+    },
+    {
+      "epoch": 0.11795543905635648,
+      "grad_norm": 2.0523645877838135,
+      "learning_rate": 0.00019976777311992247,
+      "loss": 0.5298,
+      "step": 135
+    },
+    {
+      "epoch": 0.12232415902140673,
+      "grad_norm": 2.065765619277954,
+      "learning_rate": 0.00019974867557229098,
+      "loss": 0.5228,
+      "step": 140
+    },
+    {
+      "epoch": 0.12669287898645698,
+      "grad_norm": 1.7283438444137573,
+      "learning_rate": 0.00019972882447105912,
+      "loss": 0.3452,
+      "step": 145
+    },
+    {
+      "epoch": 0.1310615989515072,
+      "grad_norm": 2.655750274658203,
+      "learning_rate": 0.00019970821996619244,
+      "loss": 0.508,
+      "step": 150
+    },
+    {
+      "epoch": 0.13543031891655744,
+      "grad_norm": 2.67799973487854,
+      "learning_rate": 0.0001996868622133482,
+      "loss": 0.4359,
+      "step": 155
+    },
+    {
+      "epoch": 0.1397990388816077,
+      "grad_norm": 1.6298809051513672,
+      "learning_rate": 0.00019966475137387396,
+      "loss": 0.5447,
+      "step": 160
+    },
+    {
+      "epoch": 0.14416775884665792,
+      "grad_norm": 1.4772286415100098,
+      "learning_rate": 0.00019964188761480657,
+      "loss": 0.4105,
+      "step": 165
+    },
+    {
+      "epoch": 0.14853647881170817,
+      "grad_norm": 2.2986271381378174,
+      "learning_rate": 0.00019961827110887083,
+      "loss": 0.603,
+      "step": 170
+    },
+    {
+      "epoch": 0.1529051987767584,
+      "grad_norm": 2.8261911869049072,
+      "learning_rate": 0.00019959390203447817,
+      "loss": 0.4649,
+      "step": 175
+    },
+    {
+      "epoch": 0.15727391874180865,
+      "grad_norm": 1.7771011590957642,
+      "learning_rate": 0.00019956878057572524,
+      "loss": 0.4394,
+      "step": 180
+    },
+    {
+      "epoch": 0.16164263870685888,
+      "grad_norm": 1.7315421104431152,
+      "learning_rate": 0.00019954290692239274,
+      "loss": 0.5289,
+      "step": 185
+    },
+    {
+      "epoch": 0.16601135867190914,
+      "grad_norm": 1.6124423742294312,
+      "learning_rate": 0.00019951628126994373,
+      "loss": 0.4173,
+      "step": 190
+    },
+    {
+      "epoch": 0.17038007863695936,
+      "grad_norm": 1.792577862739563,
+      "learning_rate": 0.00019948890381952232,
+      "loss": 0.4331,
+      "step": 195
+    },
+    {
+      "epoch": 0.17474879860200962,
+      "grad_norm": 1.9038774967193604,
+      "learning_rate": 0.000199460774777952,
+      "loss": 0.4247,
+      "step": 200
+    },
+    {
+      "epoch": 0.17911751856705985,
+      "grad_norm": 2.457122802734375,
+      "learning_rate": 0.00019943189435773432,
+      "loss": 0.4519,
+      "step": 205
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 1.97683584690094,
+      "learning_rate": 0.00019940226277704706,
+      "loss": 0.4761,
+      "step": 210
+    },
+    {
+      "epoch": 0.18785495849716033,
+      "grad_norm": 2.1646862030029297,
+      "learning_rate": 0.0001993718802597426,
+      "loss": 0.5294,
+      "step": 215
+    },
+    {
+      "epoch": 0.19222367846221058,
+      "grad_norm": 1.565412998199463,
+      "learning_rate": 0.00019934074703534637,
+      "loss": 0.3999,
+      "step": 220
+    },
+    {
+      "epoch": 0.1965923984272608,
+      "grad_norm": 2.4315876960754395,
+      "learning_rate": 0.00019930886333905504,
+      "loss": 0.378,
+      "step": 225
+    },
+    {
+      "epoch": 0.20096111839231107,
+      "grad_norm": 2.7567529678344727,
+      "learning_rate": 0.00019927622941173467,
+      "loss": 0.5075,
+      "step": 230
+    },
+    {
+      "epoch": 0.2053298383573613,
+      "grad_norm": 1.8640387058258057,
+      "learning_rate": 0.00019924284549991902,
+      "loss": 0.4749,
+      "step": 235
+    },
+    {
+      "epoch": 0.20969855832241152,
+      "grad_norm": 2.090924024581909,
+      "learning_rate": 0.00019920871185580757,
+      "loss": 0.4353,
+      "step": 240
+    },
+    {
+      "epoch": 0.21406727828746178,
+      "grad_norm": 1.9691081047058105,
+      "learning_rate": 0.00019917382873726376,
+      "loss": 0.4051,
+      "step": 245
+    },
+    {
+      "epoch": 0.218435998252512,
+      "grad_norm": 1.8130213022232056,
+      "learning_rate": 0.0001991381964078128,
+      "loss": 0.526,
+      "step": 250
+    },
+    {
+      "epoch": 0.22280471821756226,
+      "grad_norm": 2.078805923461914,
+      "learning_rate": 0.00019910181513664,
+      "loss": 0.5654,
+      "step": 255
+    },
+    {
+      "epoch": 0.22717343818261249,
+      "grad_norm": 2.0686287879943848,
+      "learning_rate": 0.0001990646851985884,
+      "loss": 0.43,
+      "step": 260
+    },
+    {
+      "epoch": 0.23154215814766274,
+      "grad_norm": 1.475821614265442,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 0.355,
+      "step": 265
+    },
+    {
+      "epoch": 0.23591087811271297,
+      "grad_norm": 1.901236891746521,
+      "learning_rate": 0.0001989881804494985,
+      "loss": 0.4522,
+      "step": 270
+    },
+    {
+      "epoch": 0.24027959807776322,
+      "grad_norm": 1.2583553791046143,
+      "learning_rate": 0.00019894880621641704,
+      "loss": 0.3869,
+      "step": 275
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 1.712336540222168,
+      "learning_rate": 0.00019890868447236613,
+      "loss": 0.454,
+      "step": 280
+    },
+    {
+      "epoch": 0.2490170380078637,
+      "grad_norm": 2.3967206478118896,
+      "learning_rate": 0.00019886781552044634,
+      "loss": 0.4074,
+      "step": 285
+    },
+    {
+      "epoch": 0.25338575797291396,
+      "grad_norm": 2.0578925609588623,
+      "learning_rate": 0.0001988261996694032,
+      "loss": 0.4268,
+      "step": 290
+    },
+    {
+      "epoch": 0.2577544779379642,
+      "grad_norm": 1.7411088943481445,
+      "learning_rate": 0.0001987838372336245,
+      "loss": 0.334,
+      "step": 295
+    },
+    {
+      "epoch": 0.2621231979030144,
+      "grad_norm": 1.8145533800125122,
+      "learning_rate": 0.0001987407285331382,
+      "loss": 0.4019,
+      "step": 300
+    },
+    {
+      "epoch": 0.26649191786806464,
+      "grad_norm": 1.3501653671264648,
+      "learning_rate": 0.00019869687389361,
+      "loss": 0.32,
+      "step": 305
+    },
+    {
+      "epoch": 0.27086063783311487,
+      "grad_norm": 1.208422303199768,
+      "learning_rate": 0.00019865227364634073,
+      "loss": 0.4548,
+      "step": 310
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 1.521690011024475,
+      "learning_rate": 0.00019860692812826396,
+      "loss": 0.3572,
+      "step": 315
+    },
+    {
+      "epoch": 0.2795980777632154,
+      "grad_norm": 2.2849714756011963,
+      "learning_rate": 0.0001985608376819434,
+      "loss": 0.4555,
+      "step": 320
+    },
+    {
+      "epoch": 0.2839667977282656,
+      "grad_norm": 2.7733798027038574,
+      "learning_rate": 0.00019851400265557037,
+      "loss": 0.4726,
+      "step": 325
+    },
+    {
+      "epoch": 0.28833551769331583,
+      "grad_norm": 1.973522424697876,
+      "learning_rate": 0.00019846642340296114,
+      "loss": 0.4585,
+      "step": 330
+    },
+    {
+      "epoch": 0.2927042376583661,
+      "grad_norm": 1.7133642435073853,
+      "learning_rate": 0.0001984181002835542,
+      "loss": 0.4679,
+      "step": 335
+    },
+    {
+      "epoch": 0.29707295762341634,
+      "grad_norm": 2.8383235931396484,
+      "learning_rate": 0.00019836903366240768,
+      "loss": 0.4119,
+      "step": 340
+    },
+    {
+      "epoch": 0.30144167758846657,
+      "grad_norm": 2.798276901245117,
+      "learning_rate": 0.00019831922391019645,
+      "loss": 0.3665,
+      "step": 345
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 2.171276569366455,
+      "learning_rate": 0.00019826867140320938,
+      "loss": 0.5691,
+      "step": 350
+    },
+    {
+      "epoch": 0.3101791175185671,
+      "grad_norm": 2.0866177082061768,
+      "learning_rate": 0.00019821737652334653,
+      "loss": 0.4074,
+      "step": 355
+    },
+    {
+      "epoch": 0.3145478374836173,
+      "grad_norm": 1.3713918924331665,
+      "learning_rate": 0.0001981653396581162,
+      "loss": 0.3379,
+      "step": 360
+    },
+    {
+      "epoch": 0.31891655744866754,
+      "grad_norm": 1.6086684465408325,
+      "learning_rate": 0.0001981125612006321,
+      "loss": 0.3563,
+      "step": 365
+    },
+    {
+      "epoch": 0.32328527741371776,
+      "grad_norm": 2.655686378479004,
+      "learning_rate": 0.0001980590415496102,
+      "loss": 0.3988,
+      "step": 370
+    },
+    {
+      "epoch": 0.32765399737876805,
+      "grad_norm": 1.5271559953689575,
+      "learning_rate": 0.00019800478110936596,
+      "loss": 0.5784,
+      "step": 375
+    },
+    {
+      "epoch": 0.3320227173438183,
+      "grad_norm": 1.3043195009231567,
+      "learning_rate": 0.00019794978028981106,
+      "loss": 0.2637,
+      "step": 380
+    },
+    {
+      "epoch": 0.3363914373088685,
+      "grad_norm": 2.539109706878662,
+      "learning_rate": 0.0001978940395064504,
+      "loss": 0.4658,
+      "step": 385
+    },
+    {
+      "epoch": 0.34076015727391873,
+      "grad_norm": 1.7521268129348755,
+      "learning_rate": 0.00019783755918037903,
+      "loss": 0.4253,
+      "step": 390
+    },
+    {
+      "epoch": 0.34512887723896896,
+      "grad_norm": 1.5679692029953003,
+      "learning_rate": 0.00019778033973827882,
+      "loss": 0.4528,
+      "step": 395
+    },
+    {
+      "epoch": 0.34949759720401924,
+      "grad_norm": 1.670640468597412,
+      "learning_rate": 0.00019772238161241528,
+      "loss": 0.3724,
+      "step": 400
+    },
+    {
+      "epoch": 0.35386631716906947,
+      "grad_norm": 1.520856261253357,
+      "learning_rate": 0.00019766368524063438,
+      "loss": 0.4141,
+      "step": 405
+    },
+    {
+      "epoch": 0.3582350371341197,
+      "grad_norm": 1.0802158117294312,
+      "learning_rate": 0.00019760425106635926,
+      "loss": 0.3268,
+      "step": 410
+    },
+    {
+      "epoch": 0.3626037570991699,
+      "grad_norm": 1.7306379079818726,
+      "learning_rate": 0.0001975440795385866,
+      "loss": 0.3654,
+      "step": 415
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 1.5037274360656738,
+      "learning_rate": 0.0001974831711118836,
+      "loss": 0.4285,
+      "step": 420
+    },
+    {
+      "epoch": 0.37134119702927043,
+      "grad_norm": 1.4654844999313354,
+      "learning_rate": 0.00019742152624638437,
+      "loss": 0.2548,
+      "step": 425
+    },
+    {
+      "epoch": 0.37570991699432066,
+      "grad_norm": 2.6770753860473633,
+      "learning_rate": 0.00019735914540778638,
+      "loss": 0.4238,
+      "step": 430
+    },
+    {
+      "epoch": 0.3800786369593709,
+      "grad_norm": 1.1864055395126343,
+      "learning_rate": 0.00019729602906734704,
+      "loss": 0.3959,
+      "step": 435
+    },
+    {
+      "epoch": 0.38444735692442117,
+      "grad_norm": 1.904876708984375,
+      "learning_rate": 0.00019723217770188024,
+      "loss": 0.3603,
+      "step": 440
+    },
+    {
+      "epoch": 0.3888160768894714,
+      "grad_norm": 1.7086598873138428,
+      "learning_rate": 0.0001971675917937525,
+      "loss": 0.551,
+      "step": 445
+    },
+    {
+      "epoch": 0.3931847968545216,
+      "grad_norm": 1.4635995626449585,
+      "learning_rate": 0.00019710227183087947,
+      "loss": 0.3738,
+      "step": 450
+    },
+    {
+      "epoch": 0.39755351681957185,
+      "grad_norm": 1.6047295331954956,
+      "learning_rate": 0.00019703621830672238,
+      "loss": 0.475,
+      "step": 455
+    },
+    {
+      "epoch": 0.40192223678462213,
+      "grad_norm": 1.4741933345794678,
+      "learning_rate": 0.00019696943172028394,
+      "loss": 0.4021,
+      "step": 460
+    },
+    {
+      "epoch": 0.40629095674967236,
+      "grad_norm": 2.8138020038604736,
+      "learning_rate": 0.00019690191257610497,
+      "loss": 0.3665,
+      "step": 465
+    },
+    {
+      "epoch": 0.4106596767147226,
+      "grad_norm": 1.6264874935150146,
+      "learning_rate": 0.00019683366138426034,
+      "loss": 0.3598,
+      "step": 470
+    },
+    {
+      "epoch": 0.4150283966797728,
+      "grad_norm": 1.6185061931610107,
+      "learning_rate": 0.00019676467866035525,
+      "loss": 0.5003,
+      "step": 475
+    },
+    {
+      "epoch": 0.41939711664482304,
+      "grad_norm": 1.8654040098190308,
+      "learning_rate": 0.00019669496492552113,
+      "loss": 0.397,
+      "step": 480
+    },
+    {
+      "epoch": 0.4237658366098733,
+      "grad_norm": 1.2525237798690796,
+      "learning_rate": 0.00019662452070641205,
+      "loss": 0.3235,
+      "step": 485
+    },
+    {
+      "epoch": 0.42813455657492355,
+      "grad_norm": 1.7755401134490967,
+      "learning_rate": 0.00019655334653520036,
+      "loss": 0.2978,
+      "step": 490
+    },
+    {
+      "epoch": 0.4325032765399738,
+      "grad_norm": 1.6025470495224,
+      "learning_rate": 0.00019648144294957297,
+      "loss": 0.4436,
+      "step": 495
+    },
+    {
+      "epoch": 0.436871996505024,
+      "grad_norm": 1.085461974143982,
+      "learning_rate": 0.00019640881049272713,
+      "loss": 0.22,
+      "step": 500
+    },
+    {
+      "epoch": 0.4412407164700743,
+      "grad_norm": 1.491818904876709,
+      "learning_rate": 0.00019633544971336636,
+      "loss": 0.2714,
+      "step": 505
+    },
+    {
+      "epoch": 0.4456094364351245,
+      "grad_norm": 0.9479840993881226,
+      "learning_rate": 0.0001962613611656963,
+      "loss": 0.3735,
+      "step": 510
+    },
+    {
+      "epoch": 0.44997815640017474,
+      "grad_norm": 3.0529448986053467,
+      "learning_rate": 0.0001961865454094205,
+      "loss": 0.4779,
+      "step": 515
+    },
+    {
+      "epoch": 0.45434687636522497,
+      "grad_norm": 2.831089973449707,
+      "learning_rate": 0.00019611100300973635,
+      "loss": 0.469,
+      "step": 520
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 2.1834311485290527,
+      "learning_rate": 0.00019603473453733052,
+      "loss": 0.4163,
+      "step": 525
+    },
+    {
+      "epoch": 0.4630843162953255,
+      "grad_norm": 1.3152204751968384,
+      "learning_rate": 0.00019595774056837493,
+      "loss": 0.3744,
+      "step": 530
+    },
+    {
+      "epoch": 0.4674530362603757,
+      "grad_norm": 1.4493387937545776,
+      "learning_rate": 0.00019588002168452223,
+      "loss": 0.3117,
+      "step": 535
+    },
+    {
+      "epoch": 0.47182175622542594,
+      "grad_norm": 1.1412076950073242,
+      "learning_rate": 0.00019580157847290147,
+      "loss": 0.3152,
+      "step": 540
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.5004645586013794,
+      "learning_rate": 0.00019572241152611365,
+      "loss": 0.3271,
+      "step": 545
+    },
+    {
+      "epoch": 0.48055919615552645,
+      "grad_norm": 2.3333992958068848,
+      "learning_rate": 0.0001956425214422272,
+      "loss": 0.3626,
+      "step": 550
+    },
+    {
+      "epoch": 0.4849279161205767,
+      "grad_norm": 1.5423107147216797,
+      "learning_rate": 0.0001955619088247736,
+      "loss": 0.4588,
+      "step": 555
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 3.008280038833618,
+      "learning_rate": 0.00019548057428274266,
+      "loss": 0.5275,
+      "step": 560
+    },
+    {
+      "epoch": 0.49366535605067713,
+      "grad_norm": 1.0968583822250366,
+      "learning_rate": 0.00019539851843057798,
+      "loss": 0.3233,
+      "step": 565
+    },
+    {
+      "epoch": 0.4980340760157274,
+      "grad_norm": 1.265228271484375,
+      "learning_rate": 0.00019531574188817234,
+      "loss": 0.2743,
+      "step": 570
+    },
+    {
+      "epoch": 0.5024027959807776,
+      "grad_norm": 1.9382916688919067,
+      "learning_rate": 0.000195232245280863,
+      "loss": 0.3189,
+      "step": 575
+    },
+    {
+      "epoch": 0.5067715159458279,
+      "grad_norm": 1.6710058450698853,
+      "learning_rate": 0.00019514802923942687,
+      "loss": 0.345,
+      "step": 580
+    },
+    {
+      "epoch": 0.5111402359108781,
+      "grad_norm": 1.8377633094787598,
+      "learning_rate": 0.000195063094400076,
+      "loss": 0.4441,
+      "step": 585
+    },
+    {
+      "epoch": 0.5155089558759284,
+      "grad_norm": 1.432173728942871,
+      "learning_rate": 0.0001949774414044525,
+      "loss": 0.3277,
+      "step": 590
+    },
+    {
+      "epoch": 0.5198776758409785,
+      "grad_norm": 1.096330165863037,
+      "learning_rate": 0.0001948910708996239,
+      "loss": 0.3821,
+      "step": 595
+    },
+    {
+      "epoch": 0.5242463958060288,
+      "grad_norm": 1.1951391696929932,
+      "learning_rate": 0.00019480398353807798,
+      "loss": 0.4303,
+      "step": 600
+    },
+    {
+      "epoch": 0.5286151157710791,
+      "grad_norm": 0.9764880537986755,
+      "learning_rate": 0.0001947161799777183,
+      "loss": 0.2693,
+      "step": 605
+    },
+    {
+      "epoch": 0.5329838357361293,
+      "grad_norm": 1.2566354274749756,
+      "learning_rate": 0.00019462766088185874,
+      "loss": 0.2851,
+      "step": 610
+    },
+    {
+      "epoch": 0.5373525557011796,
+      "grad_norm": 1.494903802871704,
+      "learning_rate": 0.0001945384269192188,
+      "loss": 0.36,
+      "step": 615
+    },
+    {
+      "epoch": 0.5417212756662297,
+      "grad_norm": 1.5508995056152344,
+      "learning_rate": 0.00019444847876391844,
+      "loss": 0.3682,
+      "step": 620
+    },
+    {
+      "epoch": 0.54608999563128,
+      "grad_norm": 2.227889060974121,
+      "learning_rate": 0.00019435781709547305,
+      "loss": 0.3889,
+      "step": 625
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.9221494197845459,
+      "learning_rate": 0.0001942664425987882,
+      "loss": 0.3375,
+      "step": 630
+    },
+    {
+      "epoch": 0.5548274355613805,
+      "grad_norm": 1.3386973142623901,
+      "learning_rate": 0.00019417435596415458,
+      "loss": 0.4833,
+      "step": 635
+    },
+    {
+      "epoch": 0.5591961555264308,
+      "grad_norm": 1.9686752557754517,
+      "learning_rate": 0.00019408155788724272,
+      "loss": 0.4739,
+      "step": 640
+    },
+    {
+      "epoch": 0.563564875491481,
+      "grad_norm": 2.3978073596954346,
+      "learning_rate": 0.00019398804906909777,
+      "loss": 0.4681,
+      "step": 645
+    },
+    {
+      "epoch": 0.5679335954565312,
+      "grad_norm": 1.536699652671814,
+      "learning_rate": 0.0001938938302161342,
+      "loss": 0.2684,
+      "step": 650
+    },
+    {
+      "epoch": 0.5723023154215815,
+      "grad_norm": 1.691787600517273,
+      "learning_rate": 0.00019379890204013043,
+      "loss": 0.3512,
+      "step": 655
+    },
+    {
+      "epoch": 0.5766710353866317,
+      "grad_norm": 1.7557870149612427,
+      "learning_rate": 0.0001937032652582235,
+      "loss": 0.3423,
+      "step": 660
+    },
+    {
+      "epoch": 0.581039755351682,
+      "grad_norm": 1.7950220108032227,
+      "learning_rate": 0.0001936069205929036,
+      "loss": 0.2831,
+      "step": 665
+    },
+    {
+      "epoch": 0.5854084753167322,
+      "grad_norm": 1.928232192993164,
+      "learning_rate": 0.00019350986877200867,
+      "loss": 0.323,
+      "step": 670
+    },
+    {
+      "epoch": 0.5897771952817824,
+      "grad_norm": 1.86429762840271,
+      "learning_rate": 0.00019341211052871887,
+      "loss": 0.4248,
+      "step": 675
+    },
+    {
+      "epoch": 0.5941459152468327,
+      "grad_norm": 2.022738456726074,
+      "learning_rate": 0.00019331364660155103,
+      "loss": 0.3411,
+      "step": 680
+    },
+    {
+      "epoch": 0.598514635211883,
+      "grad_norm": 1.2337995767593384,
+      "learning_rate": 0.00019321447773435306,
+      "loss": 0.2368,
+      "step": 685
+    },
+    {
+      "epoch": 0.6028833551769331,
+      "grad_norm": 2.015075445175171,
+      "learning_rate": 0.00019311460467629843,
+      "loss": 0.5116,
+      "step": 690
+    },
+    {
+      "epoch": 0.6072520751419834,
+      "grad_norm": 1.2344030141830444,
+      "learning_rate": 0.00019301402818188036,
+      "loss": 0.3313,
+      "step": 695
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 1.129764437675476,
+      "learning_rate": 0.00019291274901090625,
+      "loss": 0.408,
+      "step": 700
+    },
+    {
+      "epoch": 0.6159895150720839,
+      "grad_norm": 1.4350385665893555,
+      "learning_rate": 0.00019281076792849184,
+      "loss": 0.3729,
+      "step": 705
+    },
+    {
+      "epoch": 0.6203582350371342,
+      "grad_norm": 1.9586119651794434,
+      "learning_rate": 0.00019270808570505553,
+      "loss": 0.4315,
+      "step": 710
+    },
+    {
+      "epoch": 0.6247269550021843,
+      "grad_norm": 1.0157238245010376,
+      "learning_rate": 0.00019260470311631243,
+      "loss": 0.2861,
+      "step": 715
+    },
+    {
+      "epoch": 0.6290956749672346,
+      "grad_norm": 1.3841652870178223,
+      "learning_rate": 0.00019250062094326864,
+      "loss": 0.4037,
+      "step": 720
+    },
+    {
+      "epoch": 0.6334643949322848,
+      "grad_norm": 1.848821997642517,
+      "learning_rate": 0.00019239583997221525,
+      "loss": 0.3665,
+      "step": 725
+    },
+    {
+      "epoch": 0.6378331148973351,
+      "grad_norm": 0.9416481256484985,
+      "learning_rate": 0.0001922903609947225,
+      "loss": 0.339,
+      "step": 730
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 1.0696804523468018,
+      "learning_rate": 0.0001921841848076336,
+      "loss": 0.2783,
+      "step": 735
+    },
+    {
+      "epoch": 0.6465705548274355,
+      "grad_norm": 1.9199622869491577,
+      "learning_rate": 0.00019207731221305903,
+      "loss": 0.2904,
+      "step": 740
+    },
+    {
+      "epoch": 0.6509392747924858,
+      "grad_norm": 1.347430944442749,
+      "learning_rate": 0.00019196974401837008,
+      "loss": 0.2719,
+      "step": 745
+    },
+    {
+      "epoch": 0.6553079947575361,
+      "grad_norm": 0.9743670225143433,
+      "learning_rate": 0.0001918614810361932,
+      "loss": 0.2748,
+      "step": 750
+    },
+    {
+      "epoch": 0.6596767147225863,
+      "grad_norm": 1.4043099880218506,
+      "learning_rate": 0.00019175252408440343,
+      "loss": 0.3285,
+      "step": 755
+    },
+    {
+      "epoch": 0.6640454346876365,
+      "grad_norm": 2.9343338012695312,
+      "learning_rate": 0.0001916428739861185,
+      "loss": 0.4962,
+      "step": 760
+    },
+    {
+      "epoch": 0.6684141546526867,
+      "grad_norm": 2.3201515674591064,
+      "learning_rate": 0.0001915325315696926,
+      "loss": 0.3243,
+      "step": 765
+    },
+    {
+      "epoch": 0.672782874617737,
+      "grad_norm": 1.675564169883728,
+      "learning_rate": 0.00019142149766870992,
+      "loss": 0.4596,
+      "step": 770
+    },
+    {
+      "epoch": 0.6771515945827873,
+      "grad_norm": 1.664604663848877,
+      "learning_rate": 0.00019130977312197854,
+      "loss": 0.3024,
+      "step": 775
+    },
+    {
+      "epoch": 0.6815203145478375,
+      "grad_norm": 1.8358148336410522,
+      "learning_rate": 0.00019119735877352412,
+      "loss": 0.3862,
+      "step": 780
+    },
+    {
+      "epoch": 0.6858890345128877,
+      "grad_norm": 1.3632128238677979,
+      "learning_rate": 0.00019108425547258328,
+      "loss": 0.2374,
+      "step": 785
+    },
+    {
+      "epoch": 0.6902577544779379,
+      "grad_norm": 2.0279934406280518,
+      "learning_rate": 0.0001909704640735975,
+      "loss": 0.4392,
+      "step": 790
+    },
+    {
+      "epoch": 0.6946264744429882,
+      "grad_norm": 1.2824902534484863,
+      "learning_rate": 0.0001908559854362064,
+      "loss": 0.2782,
+      "step": 795
+    },
+    {
+      "epoch": 0.6989951944080385,
+      "grad_norm": 1.3477047681808472,
+      "learning_rate": 0.00019074082042524145,
+      "loss": 0.3631,
+      "step": 800
+    },
+    {
+      "epoch": 0.7033639143730887,
+      "grad_norm": 1.8478046655654907,
+      "learning_rate": 0.00019062496991071928,
+      "loss": 0.3788,
+      "step": 805
+    },
+    {
+      "epoch": 0.7077326343381389,
+      "grad_norm": 1.470382571220398,
+      "learning_rate": 0.0001905084347678352,
+      "loss": 0.3825,
+      "step": 810
+    },
+    {
+      "epoch": 0.7121013543031892,
+      "grad_norm": 2.4951813220977783,
+      "learning_rate": 0.00019039121587695652,
+      "loss": 0.3359,
+      "step": 815
+    },
+    {
+      "epoch": 0.7164700742682394,
+      "grad_norm": 2.3441359996795654,
+      "learning_rate": 0.000190273314123616,
+      "loss": 0.32,
+      "step": 820
+    },
+    {
+      "epoch": 0.7208387942332897,
+      "grad_norm": 2.372884750366211,
+      "learning_rate": 0.00019015473039850513,
+      "loss": 0.3651,
+      "step": 825
+    },
+    {
+      "epoch": 0.7252075141983398,
+      "grad_norm": 2.4474101066589355,
+      "learning_rate": 0.0001900354655974672,
+      "loss": 0.4401,
+      "step": 830
+    },
+    {
+      "epoch": 0.7295762341633901,
+      "grad_norm": 1.4031054973602295,
+      "learning_rate": 0.0001899155206214909,
+      "loss": 0.308,
+      "step": 835
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 1.6008141040802002,
+      "learning_rate": 0.00018979489637670322,
+      "loss": 0.2937,
+      "step": 840
+    },
+    {
+      "epoch": 0.7383136740934906,
+      "grad_norm": 0.9202178120613098,
+      "learning_rate": 0.0001896735937743627,
+      "loss": 0.3157,
+      "step": 845
+    },
+    {
+      "epoch": 0.7426823940585409,
+      "grad_norm": 1.024746298789978,
+      "learning_rate": 0.00018955161373085253,
+      "loss": 0.2934,
+      "step": 850
+    },
+    {
+      "epoch": 0.747051114023591,
+      "grad_norm": 1.1573566198349,
+      "learning_rate": 0.00018942895716767374,
+      "loss": 0.3617,
+      "step": 855
+    },
+    {
+      "epoch": 0.7514198339886413,
+      "grad_norm": 1.227409839630127,
+      "learning_rate": 0.00018930562501143805,
+      "loss": 0.3581,
+      "step": 860
+    },
+    {
+      "epoch": 0.7557885539536916,
+      "grad_norm": 1.5460100173950195,
+      "learning_rate": 0.00018918161819386095,
+      "loss": 0.3393,
+      "step": 865
+    },
+    {
+      "epoch": 0.7601572739187418,
+      "grad_norm": 1.688852310180664,
+      "learning_rate": 0.0001890569376517548,
+      "loss": 0.4389,
+      "step": 870
+    },
+    {
+      "epoch": 0.764525993883792,
+      "grad_norm": 1.5271598100662231,
+      "learning_rate": 0.00018893158432702149,
+      "loss": 0.2915,
+      "step": 875
+    },
+    {
+      "epoch": 0.7688947138488423,
+      "grad_norm": 1.695788860321045,
+      "learning_rate": 0.00018880555916664555,
+      "loss": 0.4026,
+      "step": 880
+    },
+    {
+      "epoch": 0.7732634338138925,
+      "grad_norm": 1.6879792213439941,
+      "learning_rate": 0.00018867886312268683,
+      "loss": 0.2857,
+      "step": 885
+    },
+    {
+      "epoch": 0.7776321537789428,
+      "grad_norm": 2.0718719959259033,
+      "learning_rate": 0.00018855149715227344,
+      "loss": 0.4236,
+      "step": 890
+    },
+    {
+      "epoch": 0.782000873743993,
+      "grad_norm": 1.5112775564193726,
+      "learning_rate": 0.00018842346221759448,
+      "loss": 0.325,
+      "step": 895
+    },
+    {
+      "epoch": 0.7863695937090432,
+      "grad_norm": 1.2844749689102173,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 0.3782,
+      "step": 900
+    },
+    {
+      "epoch": 0.7907383136740935,
+      "grad_norm": 2.150299072265625,
+      "learning_rate": 0.00018816538932945728,
+      "loss": 0.3726,
+      "step": 905
+    },
+    {
+      "epoch": 0.7951070336391437,
+      "grad_norm": 1.7050650119781494,
+      "learning_rate": 0.00018803535332561646,
+      "loss": 0.3824,
+      "step": 910
+    },
+    {
+      "epoch": 0.799475753604194,
+      "grad_norm": 1.8164982795715332,
+      "learning_rate": 0.00018790465225673012,
+      "loss": 0.3664,
+      "step": 915
+    },
+    {
+      "epoch": 0.8038444735692443,
+      "grad_norm": 1.1102941036224365,
+      "learning_rate": 0.00018777328711018244,
+      "loss": 0.3166,
+      "step": 920
+    },
+    {
+      "epoch": 0.8082131935342944,
+      "grad_norm": 1.4220764636993408,
+      "learning_rate": 0.0001876412588783743,
+      "loss": 0.3049,
+      "step": 925
+    },
+    {
+      "epoch": 0.8125819134993447,
+      "grad_norm": 2.11336088180542,
+      "learning_rate": 0.000187508568558716,
+      "loss": 0.3076,
+      "step": 930
+    },
+    {
+      "epoch": 0.8169506334643949,
+      "grad_norm": 1.9948710203170776,
+      "learning_rate": 0.00018737521715361948,
+      "loss": 0.3846,
+      "step": 935
+    },
+    {
+      "epoch": 0.8213193534294452,
+      "grad_norm": 1.8913676738739014,
+      "learning_rate": 0.00018724120567049094,
+      "loss": 0.4296,
+      "step": 940
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 1.3633447885513306,
+      "learning_rate": 0.0001871065351217231,
+      "loss": 0.3569,
+      "step": 945
+    },
+    {
+      "epoch": 0.8300567933595456,
+      "grad_norm": 1.4957417249679565,
+      "learning_rate": 0.00018697120652468762,
+      "loss": 0.3085,
+      "step": 950
+    },
+    {
+      "epoch": 0.8344255133245959,
+      "grad_norm": 2.076399803161621,
+      "learning_rate": 0.0001868352209017275,
+      "loss": 0.3331,
+      "step": 955
+    },
+    {
+      "epoch": 0.8387942332896461,
+      "grad_norm": 1.1817855834960938,
+      "learning_rate": 0.00018669857928014906,
+      "loss": 0.3414,
+      "step": 960
+    },
+    {
+      "epoch": 0.8431629532546964,
+      "grad_norm": 1.4255414009094238,
+      "learning_rate": 0.00018656128269221454,
+      "loss": 0.2782,
+      "step": 965
+    },
+    {
+      "epoch": 0.8475316732197467,
+      "grad_norm": 1.326687216758728,
+      "learning_rate": 0.0001864233321751341,
+      "loss": 0.2998,
+      "step": 970
+    },
+    {
+      "epoch": 0.8519003931847968,
+      "grad_norm": 2.222280263900757,
+      "learning_rate": 0.00018628472877105793,
+      "loss": 0.3348,
+      "step": 975
+    },
+    {
+      "epoch": 0.8562691131498471,
+      "grad_norm": 1.518401026725769,
+      "learning_rate": 0.00018614547352706863,
+      "loss": 0.3816,
+      "step": 980
+    },
+    {
+      "epoch": 0.8606378331148974,
+      "grad_norm": 1.1030207872390747,
+      "learning_rate": 0.00018600556749517305,
+      "loss": 0.3222,
+      "step": 985
+    },
+    {
+      "epoch": 0.8650065530799476,
+      "grad_norm": 2.406994104385376,
+      "learning_rate": 0.00018586501173229437,
+      "loss": 0.3754,
+      "step": 990
+    },
+    {
+      "epoch": 0.8693752730449978,
+      "grad_norm": 1.2401646375656128,
+      "learning_rate": 0.00018572380730026434,
+      "loss": 0.4402,
+      "step": 995
+    },
+    {
+      "epoch": 0.873743993010048,
+      "grad_norm": 2.0233402252197266,
+      "learning_rate": 0.0001855819552658149,
+      "loss": 0.3323,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5725,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 485735378608128.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629a35960f565450f5c9e65334fb9c14eb136182b8af4bc22c885bdde32de5f3
+size 5777

checkpoint-1100/README.md

@@ -0,0 +1,207 @@
+---
+base_model: unsloth/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/functiongemma-270m-it
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1100/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/functiongemma-270m-it",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa7e5dcebe3d84bc2f13e835e8c7c167e2bd913f8acb028dace29615ac4a2ab
+size 60785144

checkpoint-1100/added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<end_of_image>": 262145,
+  "<image_soft_token>": 262144
+}

checkpoint-1100/chat_template.jinja

@@ -0,0 +1,282 @@
+{%- 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:] -%}
+    {%- else -%}
+        {{- 'You are a model that can do function calling with the following functions' -}}
+        {%- set loop_messages = messages -%}
+    {%- 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-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbc3235ecf9adc47a1cd14cefc2f03e87bcb237ac474db8b3f600fcc811cd54
+size 121708939

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb03eac9b58e52273c3aa5727841719fd6c82afc9062bbaf8eb6f842de779278
+size 14391

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c9ae0af668f7241f64d293f2b41e3dfe0e41af6f89f5b50e74617068844c5e
+size 1465

checkpoint-1100/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": "<end_of_turn>",
+    "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-1100/tokenizer.json

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

checkpoint-1100/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa009fcbc3589a9904d30d04834094fea4653c2ac6d2de2cd1262d4f7a50ceb3
+size 4689144

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9611183923110529,
+  "eval_steps": 500,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00436871996505024,
+      "grad_norm": 9.839941024780273,
+      "learning_rate": 8e-05,
+      "loss": 2.5246,
+      "step": 5
+    },
+    {
+      "epoch": 0.00873743993010048,
+      "grad_norm": 13.773455619812012,
+      "learning_rate": 0.00018,
+      "loss": 1.1343,
+      "step": 10
+    },
+    {
+      "epoch": 0.01310615989515072,
+      "grad_norm": 5.6580424308776855,
+      "learning_rate": 0.0001999997582552296,
+      "loss": 0.7712,
+      "step": 15
+    },
+    {
+      "epoch": 0.01747487986020096,
+      "grad_norm": 5.294467926025391,
+      "learning_rate": 0.0001999987761691029,
+      "loss": 0.73,
+      "step": 20
+    },
+    {
+      "epoch": 0.021843599825251202,
+      "grad_norm": 2.8633503913879395,
+      "learning_rate": 0.00019999703863998527,
+      "loss": 0.7289,
+      "step": 25
+    },
+    {
+      "epoch": 0.02621231979030144,
+      "grad_norm": 3.2836177349090576,
+      "learning_rate": 0.00019999454568100293,
+      "loss": 0.4686,
+      "step": 30
+    },
+    {
+      "epoch": 0.03058103975535168,
+      "grad_norm": 4.878258228302002,
+      "learning_rate": 0.00019999129731098898,
+      "loss": 0.6629,
+      "step": 35
+    },
+    {
+      "epoch": 0.03494975972040192,
+      "grad_norm": 2.899914026260376,
+      "learning_rate": 0.00019998729355448326,
+      "loss": 0.6038,
+      "step": 40
+    },
+    {
+      "epoch": 0.039318479685452164,
+      "grad_norm": 3.289844274520874,
+      "learning_rate": 0.00019998253444173235,
+      "loss": 0.4573,
+      "step": 45
+    },
+    {
+      "epoch": 0.043687199650502405,
+      "grad_norm": 2.957254648208618,
+      "learning_rate": 0.00019997702000868896,
+      "loss": 0.594,
+      "step": 50
+    },
+    {
+      "epoch": 0.048055919615552646,
+      "grad_norm": 3.171276807785034,
+      "learning_rate": 0.00019997075029701207,
+      "loss": 0.5719,
+      "step": 55
+    },
+    {
+      "epoch": 0.05242463958060288,
+      "grad_norm": 2.55605149269104,
+      "learning_rate": 0.0001999637253540663,
+      "loss": 0.5971,
+      "step": 60
+    },
+    {
+      "epoch": 0.05679335954565312,
+      "grad_norm": 2.127289295196533,
+      "learning_rate": 0.00019995594523292178,
+      "loss": 0.5712,
+      "step": 65
+    },
+    {
+      "epoch": 0.06116207951070336,
+      "grad_norm": 3.3928685188293457,
+      "learning_rate": 0.00019994740999235359,
+      "loss": 0.5712,
+      "step": 70
+    },
+    {
+      "epoch": 0.0655307994757536,
+      "grad_norm": 2.6700279712677,
+      "learning_rate": 0.00019993811969684142,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "epoch": 0.06989951944080385,
+      "grad_norm": 2.6936633586883545,
+      "learning_rate": 0.00019992807441656898,
+      "loss": 0.5321,
+      "step": 80
+    },
+    {
+      "epoch": 0.07426823940585409,
+      "grad_norm": 3.9897687435150146,
+      "learning_rate": 0.00019991727422742362,
+      "loss": 0.6025,
+      "step": 85
+    },
+    {
+      "epoch": 0.07863695937090433,
+      "grad_norm": 2.3496663570404053,
+      "learning_rate": 0.00019990571921099553,
+      "loss": 0.5975,
+      "step": 90
+    },
+    {
+      "epoch": 0.08300567933595457,
+      "grad_norm": 3.3796467781066895,
+      "learning_rate": 0.0001998934094545774,
+      "loss": 0.5255,
+      "step": 95
+    },
+    {
+      "epoch": 0.08737439930100481,
+      "grad_norm": 3.1103007793426514,
+      "learning_rate": 0.00019988034505116352,
+      "loss": 0.4946,
+      "step": 100
+    },
+    {
+      "epoch": 0.09174311926605505,
+      "grad_norm": 2.002304792404175,
+      "learning_rate": 0.00019986652609944926,
+      "loss": 0.425,
+      "step": 105
+    },
+    {
+      "epoch": 0.09611183923110529,
+      "grad_norm": 1.7572168111801147,
+      "learning_rate": 0.00019985195270383018,
+      "loss": 0.6073,
+      "step": 110
+    },
+    {
+      "epoch": 0.10048055919615553,
+      "grad_norm": 2.745215654373169,
+      "learning_rate": 0.00019983662497440133,
+      "loss": 0.586,
+      "step": 115
+    },
+    {
+      "epoch": 0.10484927916120576,
+      "grad_norm": 1.8170915842056274,
+      "learning_rate": 0.0001998205430269564,
+      "loss": 0.5255,
+      "step": 120
+    },
+    {
+      "epoch": 0.109217999126256,
+      "grad_norm": 1.4944056272506714,
+      "learning_rate": 0.00019980370698298677,
+      "loss": 0.4219,
+      "step": 125
+    },
+    {
+      "epoch": 0.11358671909130624,
+      "grad_norm": 1.6616989374160767,
+      "learning_rate": 0.00019978611696968074,
+      "loss": 0.4231,
+      "step": 130
+    },
+    {
+      "epoch": 0.11795543905635648,
+      "grad_norm": 2.0523645877838135,
+      "learning_rate": 0.00019976777311992247,
+      "loss": 0.5298,
+      "step": 135
+    },
+    {
+      "epoch": 0.12232415902140673,
+      "grad_norm": 2.065765619277954,
+      "learning_rate": 0.00019974867557229098,
+      "loss": 0.5228,
+      "step": 140
+    },
+    {
+      "epoch": 0.12669287898645698,
+      "grad_norm": 1.7283438444137573,
+      "learning_rate": 0.00019972882447105912,
+      "loss": 0.3452,
+      "step": 145
+    },
+    {
+      "epoch": 0.1310615989515072,
+      "grad_norm": 2.655750274658203,
+      "learning_rate": 0.00019970821996619244,
+      "loss": 0.508,
+      "step": 150
+    },
+    {
+      "epoch": 0.13543031891655744,
+      "grad_norm": 2.67799973487854,
+      "learning_rate": 0.0001996868622133482,
+      "loss": 0.4359,
+      "step": 155
+    },
+    {
+      "epoch": 0.1397990388816077,
+      "grad_norm": 1.6298809051513672,
+      "learning_rate": 0.00019966475137387396,
+      "loss": 0.5447,
+      "step": 160
+    },
+    {
+      "epoch": 0.14416775884665792,
+      "grad_norm": 1.4772286415100098,
+      "learning_rate": 0.00019964188761480657,
+      "loss": 0.4105,
+      "step": 165
+    },
+    {
+      "epoch": 0.14853647881170817,
+      "grad_norm": 2.2986271381378174,
+      "learning_rate": 0.00019961827110887083,
+      "loss": 0.603,
+      "step": 170
+    },
+    {
+      "epoch": 0.1529051987767584,
+      "grad_norm": 2.8261911869049072,
+      "learning_rate": 0.00019959390203447817,
+      "loss": 0.4649,
+      "step": 175
+    },
+    {
+      "epoch": 0.15727391874180865,
+      "grad_norm": 1.7771011590957642,
+      "learning_rate": 0.00019956878057572524,
+      "loss": 0.4394,
+      "step": 180
+    },
+    {
+      "epoch": 0.16164263870685888,
+      "grad_norm": 1.7315421104431152,
+      "learning_rate": 0.00019954290692239274,
+      "loss": 0.5289,
+      "step": 185
+    },
+    {
+      "epoch": 0.16601135867190914,
+      "grad_norm": 1.6124423742294312,
+      "learning_rate": 0.00019951628126994373,
+      "loss": 0.4173,
+      "step": 190
+    },
+    {
+      "epoch": 0.17038007863695936,
+      "grad_norm": 1.792577862739563,
+      "learning_rate": 0.00019948890381952232,
+      "loss": 0.4331,
+      "step": 195
+    },
+    {
+      "epoch": 0.17474879860200962,
+      "grad_norm": 1.9038774967193604,
+      "learning_rate": 0.000199460774777952,
+      "loss": 0.4247,
+      "step": 200
+    },
+    {
+      "epoch": 0.17911751856705985,
+      "grad_norm": 2.457122802734375,
+      "learning_rate": 0.00019943189435773432,
+      "loss": 0.4519,
+      "step": 205
+    },
+    {
+      "epoch": 0.1834862385321101,
+      "grad_norm": 1.97683584690094,
+      "learning_rate": 0.00019940226277704706,
+      "loss": 0.4761,
+      "step": 210
+    },
+    {
+      "epoch": 0.18785495849716033,
+      "grad_norm": 2.1646862030029297,
+      "learning_rate": 0.0001993718802597426,
+      "loss": 0.5294,
+      "step": 215
+    },
+    {
+      "epoch": 0.19222367846221058,
+      "grad_norm": 1.565412998199463,
+      "learning_rate": 0.00019934074703534637,
+      "loss": 0.3999,
+      "step": 220
+    },
+    {
+      "epoch": 0.1965923984272608,
+      "grad_norm": 2.4315876960754395,
+      "learning_rate": 0.00019930886333905504,
+      "loss": 0.378,
+      "step": 225
+    },
+    {
+      "epoch": 0.20096111839231107,
+      "grad_norm": 2.7567529678344727,
+      "learning_rate": 0.00019927622941173467,
+      "loss": 0.5075,
+      "step": 230
+    },
+    {
+      "epoch": 0.2053298383573613,
+      "grad_norm": 1.8640387058258057,
+      "learning_rate": 0.00019924284549991902,
+      "loss": 0.4749,
+      "step": 235
+    },
+    {
+      "epoch": 0.20969855832241152,
+      "grad_norm": 2.090924024581909,
+      "learning_rate": 0.00019920871185580757,
+      "loss": 0.4353,
+      "step": 240
+    },
+    {
+      "epoch": 0.21406727828746178,
+      "grad_norm": 1.9691081047058105,
+      "learning_rate": 0.00019917382873726376,
+      "loss": 0.4051,
+      "step": 245
+    },
+    {
+      "epoch": 0.218435998252512,
+      "grad_norm": 1.8130213022232056,
+      "learning_rate": 0.0001991381964078128,
+      "loss": 0.526,
+      "step": 250
+    },
+    {
+      "epoch": 0.22280471821756226,
+      "grad_norm": 2.078805923461914,
+      "learning_rate": 0.00019910181513664,
+      "loss": 0.5654,
+      "step": 255
+    },
+    {
+      "epoch": 0.22717343818261249,
+      "grad_norm": 2.0686287879943848,
+      "learning_rate": 0.0001990646851985884,
+      "loss": 0.43,
+      "step": 260
+    },
+    {
+      "epoch": 0.23154215814766274,
+      "grad_norm": 1.475821614265442,
+      "learning_rate": 0.00019902680687415705,
+      "loss": 0.355,
+      "step": 265
+    },
+    {
+      "epoch": 0.23591087811271297,
+      "grad_norm": 1.901236891746521,
+      "learning_rate": 0.0001989881804494985,
+      "loss": 0.4522,
+      "step": 270
+    },
+    {
+      "epoch": 0.24027959807776322,
+      "grad_norm": 1.2583553791046143,
+      "learning_rate": 0.00019894880621641704,
+      "loss": 0.3869,
+      "step": 275
+    },
+    {
+      "epoch": 0.24464831804281345,
+      "grad_norm": 1.712336540222168,
+      "learning_rate": 0.00019890868447236613,
+      "loss": 0.454,
+      "step": 280
+    },
+    {
+      "epoch": 0.2490170380078637,
+      "grad_norm": 2.3967206478118896,
+      "learning_rate": 0.00019886781552044634,
+      "loss": 0.4074,
+      "step": 285
+    },
+    {
+      "epoch": 0.25338575797291396,
+      "grad_norm": 2.0578925609588623,
+      "learning_rate": 0.0001988261996694032,
+      "loss": 0.4268,
+      "step": 290
+    },
+    {
+      "epoch": 0.2577544779379642,
+      "grad_norm": 1.7411088943481445,
+      "learning_rate": 0.0001987838372336245,
+      "loss": 0.334,
+      "step": 295
+    },
+    {
+      "epoch": 0.2621231979030144,
+      "grad_norm": 1.8145533800125122,
+      "learning_rate": 0.0001987407285331382,
+      "loss": 0.4019,
+      "step": 300
+    },
+    {
+      "epoch": 0.26649191786806464,
+      "grad_norm": 1.3501653671264648,
+      "learning_rate": 0.00019869687389361,
+      "loss": 0.32,
+      "step": 305
+    },
+    {
+      "epoch": 0.27086063783311487,
+      "grad_norm": 1.208422303199768,
+      "learning_rate": 0.00019865227364634073,
+      "loss": 0.4548,
+      "step": 310
+    },
+    {
+      "epoch": 0.27522935779816515,
+      "grad_norm": 1.521690011024475,
+      "learning_rate": 0.00019860692812826396,
+      "loss": 0.3572,
+      "step": 315
+    },
+    {
+      "epoch": 0.2795980777632154,
+      "grad_norm": 2.2849714756011963,
+      "learning_rate": 0.0001985608376819434,
+      "loss": 0.4555,
+      "step": 320
+    },
+    {
+      "epoch": 0.2839667977282656,
+      "grad_norm": 2.7733798027038574,
+      "learning_rate": 0.00019851400265557037,
+      "loss": 0.4726,
+      "step": 325
+    },
+    {
+      "epoch": 0.28833551769331583,
+      "grad_norm": 1.973522424697876,
+      "learning_rate": 0.00019846642340296114,
+      "loss": 0.4585,
+      "step": 330
+    },
+    {
+      "epoch": 0.2927042376583661,
+      "grad_norm": 1.7133642435073853,
+      "learning_rate": 0.0001984181002835542,
+      "loss": 0.4679,
+      "step": 335
+    },
+    {
+      "epoch": 0.29707295762341634,
+      "grad_norm": 2.8383235931396484,
+      "learning_rate": 0.00019836903366240768,
+      "loss": 0.4119,
+      "step": 340
+    },
+    {
+      "epoch": 0.30144167758846657,
+      "grad_norm": 2.798276901245117,
+      "learning_rate": 0.00019831922391019645,
+      "loss": 0.3665,
+      "step": 345
+    },
+    {
+      "epoch": 0.3058103975535168,
+      "grad_norm": 2.171276569366455,
+      "learning_rate": 0.00019826867140320938,
+      "loss": 0.5691,
+      "step": 350
+    },
+    {
+      "epoch": 0.3101791175185671,
+      "grad_norm": 2.0866177082061768,
+      "learning_rate": 0.00019821737652334653,
+      "loss": 0.4074,
+      "step": 355
+    },
+    {
+      "epoch": 0.3145478374836173,
+      "grad_norm": 1.3713918924331665,
+      "learning_rate": 0.0001981653396581162,
+      "loss": 0.3379,
+      "step": 360
+    },
+    {
+      "epoch": 0.31891655744866754,
+      "grad_norm": 1.6086684465408325,
+      "learning_rate": 0.0001981125612006321,
+      "loss": 0.3563,
+      "step": 365
+    },
+    {
+      "epoch": 0.32328527741371776,
+      "grad_norm": 2.655686378479004,
+      "learning_rate": 0.0001980590415496102,
+      "loss": 0.3988,
+      "step": 370
+    },
+    {
+      "epoch": 0.32765399737876805,
+      "grad_norm": 1.5271559953689575,
+      "learning_rate": 0.00019800478110936596,
+      "loss": 0.5784,
+      "step": 375
+    },
+    {
+      "epoch": 0.3320227173438183,
+      "grad_norm": 1.3043195009231567,
+      "learning_rate": 0.00019794978028981106,
+      "loss": 0.2637,
+      "step": 380
+    },
+    {
+      "epoch": 0.3363914373088685,
+      "grad_norm": 2.539109706878662,
+      "learning_rate": 0.0001978940395064504,
+      "loss": 0.4658,
+      "step": 385
+    },
+    {
+      "epoch": 0.34076015727391873,
+      "grad_norm": 1.7521268129348755,
+      "learning_rate": 0.00019783755918037903,
+      "loss": 0.4253,
+      "step": 390
+    },
+    {
+      "epoch": 0.34512887723896896,
+      "grad_norm": 1.5679692029953003,
+      "learning_rate": 0.00019778033973827882,
+      "loss": 0.4528,
+      "step": 395
+    },
+    {
+      "epoch": 0.34949759720401924,
+      "grad_norm": 1.670640468597412,
+      "learning_rate": 0.00019772238161241528,
+      "loss": 0.3724,
+      "step": 400
+    },
+    {
+      "epoch": 0.35386631716906947,
+      "grad_norm": 1.520856261253357,
+      "learning_rate": 0.00019766368524063438,
+      "loss": 0.4141,
+      "step": 405
+    },
+    {
+      "epoch": 0.3582350371341197,
+      "grad_norm": 1.0802158117294312,
+      "learning_rate": 0.00019760425106635926,
+      "loss": 0.3268,
+      "step": 410
+    },
+    {
+      "epoch": 0.3626037570991699,
+      "grad_norm": 1.7306379079818726,
+      "learning_rate": 0.0001975440795385866,
+      "loss": 0.3654,
+      "step": 415
+    },
+    {
+      "epoch": 0.3669724770642202,
+      "grad_norm": 1.5037274360656738,
+      "learning_rate": 0.0001974831711118836,
+      "loss": 0.4285,
+      "step": 420
+    },
+    {
+      "epoch": 0.37134119702927043,
+      "grad_norm": 1.4654844999313354,
+      "learning_rate": 0.00019742152624638437,
+      "loss": 0.2548,
+      "step": 425
+    },
+    {
+      "epoch": 0.37570991699432066,
+      "grad_norm": 2.6770753860473633,
+      "learning_rate": 0.00019735914540778638,
+      "loss": 0.4238,
+      "step": 430
+    },
+    {
+      "epoch": 0.3800786369593709,
+      "grad_norm": 1.1864055395126343,
+      "learning_rate": 0.00019729602906734704,
+      "loss": 0.3959,
+      "step": 435
+    },
+    {
+      "epoch": 0.38444735692442117,
+      "grad_norm": 1.904876708984375,
+      "learning_rate": 0.00019723217770188024,
+      "loss": 0.3603,
+      "step": 440
+    },
+    {
+      "epoch": 0.3888160768894714,
+      "grad_norm": 1.7086598873138428,
+      "learning_rate": 0.0001971675917937525,
+      "loss": 0.551,
+      "step": 445
+    },
+    {
+      "epoch": 0.3931847968545216,
+      "grad_norm": 1.4635995626449585,
+      "learning_rate": 0.00019710227183087947,
+      "loss": 0.3738,
+      "step": 450
+    },
+    {
+      "epoch": 0.39755351681957185,
+      "grad_norm": 1.6047295331954956,
+      "learning_rate": 0.00019703621830672238,
+      "loss": 0.475,
+      "step": 455
+    },
+    {
+      "epoch": 0.40192223678462213,
+      "grad_norm": 1.4741933345794678,
+      "learning_rate": 0.00019696943172028394,
+      "loss": 0.4021,
+      "step": 460
+    },
+    {
+      "epoch": 0.40629095674967236,
+      "grad_norm": 2.8138020038604736,
+      "learning_rate": 0.00019690191257610497,
+      "loss": 0.3665,
+      "step": 465
+    },
+    {
+      "epoch": 0.4106596767147226,
+      "grad_norm": 1.6264874935150146,
+      "learning_rate": 0.00019683366138426034,
+      "loss": 0.3598,
+      "step": 470
+    },
+    {
+      "epoch": 0.4150283966797728,
+      "grad_norm": 1.6185061931610107,
+      "learning_rate": 0.00019676467866035525,
+      "loss": 0.5003,
+      "step": 475
+    },
+    {
+      "epoch": 0.41939711664482304,
+      "grad_norm": 1.8654040098190308,
+      "learning_rate": 0.00019669496492552113,
+      "loss": 0.397,
+      "step": 480
+    },
+    {
+      "epoch": 0.4237658366098733,
+      "grad_norm": 1.2525237798690796,
+      "learning_rate": 0.00019662452070641205,
+      "loss": 0.3235,
+      "step": 485
+    },
+    {
+      "epoch": 0.42813455657492355,
+      "grad_norm": 1.7755401134490967,
+      "learning_rate": 0.00019655334653520036,
+      "loss": 0.2978,
+      "step": 490
+    },
+    {
+      "epoch": 0.4325032765399738,
+      "grad_norm": 1.6025470495224,
+      "learning_rate": 0.00019648144294957297,
+      "loss": 0.4436,
+      "step": 495
+    },
+    {
+      "epoch": 0.436871996505024,
+      "grad_norm": 1.085461974143982,
+      "learning_rate": 0.00019640881049272713,
+      "loss": 0.22,
+      "step": 500
+    },
+    {
+      "epoch": 0.4412407164700743,
+      "grad_norm": 1.491818904876709,
+      "learning_rate": 0.00019633544971336636,
+      "loss": 0.2714,
+      "step": 505
+    },
+    {
+      "epoch": 0.4456094364351245,
+      "grad_norm": 0.9479840993881226,
+      "learning_rate": 0.0001962613611656963,
+      "loss": 0.3735,
+      "step": 510
+    },
+    {
+      "epoch": 0.44997815640017474,
+      "grad_norm": 3.0529448986053467,
+      "learning_rate": 0.0001961865454094205,
+      "loss": 0.4779,
+      "step": 515
+    },
+    {
+      "epoch": 0.45434687636522497,
+      "grad_norm": 2.831089973449707,
+      "learning_rate": 0.00019611100300973635,
+      "loss": 0.469,
+      "step": 520
+    },
+    {
+      "epoch": 0.45871559633027525,
+      "grad_norm": 2.1834311485290527,
+      "learning_rate": 0.00019603473453733052,
+      "loss": 0.4163,
+      "step": 525
+    },
+    {
+      "epoch": 0.4630843162953255,
+      "grad_norm": 1.3152204751968384,
+      "learning_rate": 0.00019595774056837493,
+      "loss": 0.3744,
+      "step": 530
+    },
+    {
+      "epoch": 0.4674530362603757,
+      "grad_norm": 1.4493387937545776,
+      "learning_rate": 0.00019588002168452223,
+      "loss": 0.3117,
+      "step": 535
+    },
+    {
+      "epoch": 0.47182175622542594,
+      "grad_norm": 1.1412076950073242,
+      "learning_rate": 0.00019580157847290147,
+      "loss": 0.3152,
+      "step": 540
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.5004645586013794,
+      "learning_rate": 0.00019572241152611365,
+      "loss": 0.3271,
+      "step": 545
+    },
+    {
+      "epoch": 0.48055919615552645,
+      "grad_norm": 2.3333992958068848,
+      "learning_rate": 0.0001956425214422272,
+      "loss": 0.3626,
+      "step": 550
+    },
+    {
+      "epoch": 0.4849279161205767,
+      "grad_norm": 1.5423107147216797,
+      "learning_rate": 0.0001955619088247736,
+      "loss": 0.4588,
+      "step": 555
+    },
+    {
+      "epoch": 0.4892966360856269,
+      "grad_norm": 3.008280038833618,
+      "learning_rate": 0.00019548057428274266,
+      "loss": 0.5275,
+      "step": 560
+    },
+    {
+      "epoch": 0.49366535605067713,
+      "grad_norm": 1.0968583822250366,
+      "learning_rate": 0.00019539851843057798,
+      "loss": 0.3233,
+      "step": 565
+    },
+    {
+      "epoch": 0.4980340760157274,
+      "grad_norm": 1.265228271484375,
+      "learning_rate": 0.00019531574188817234,
+      "loss": 0.2743,
+      "step": 570
+    },
+    {
+      "epoch": 0.5024027959807776,
+      "grad_norm": 1.9382916688919067,
+      "learning_rate": 0.000195232245280863,
+      "loss": 0.3189,
+      "step": 575
+    },
+    {
+      "epoch": 0.5067715159458279,
+      "grad_norm": 1.6710058450698853,
+      "learning_rate": 0.00019514802923942687,
+      "loss": 0.345,
+      "step": 580
+    },
+    {
+      "epoch": 0.5111402359108781,
+      "grad_norm": 1.8377633094787598,
+      "learning_rate": 0.000195063094400076,
+      "loss": 0.4441,
+      "step": 585
+    },
+    {
+      "epoch": 0.5155089558759284,
+      "grad_norm": 1.432173728942871,
+      "learning_rate": 0.0001949774414044525,
+      "loss": 0.3277,
+      "step": 590
+    },
+    {
+      "epoch": 0.5198776758409785,
+      "grad_norm": 1.096330165863037,
+      "learning_rate": 0.0001948910708996239,
+      "loss": 0.3821,
+      "step": 595
+    },
+    {
+      "epoch": 0.5242463958060288,
+      "grad_norm": 1.1951391696929932,
+      "learning_rate": 0.00019480398353807798,
+      "loss": 0.4303,
+      "step": 600
+    },
+    {
+      "epoch": 0.5286151157710791,
+      "grad_norm": 0.9764880537986755,
+      "learning_rate": 0.0001947161799777183,
+      "loss": 0.2693,
+      "step": 605
+    },
+    {
+      "epoch": 0.5329838357361293,
+      "grad_norm": 1.2566354274749756,
+      "learning_rate": 0.00019462766088185874,
+      "loss": 0.2851,
+      "step": 610
+    },
+    {
+      "epoch": 0.5373525557011796,
+      "grad_norm": 1.494903802871704,
+      "learning_rate": 0.0001945384269192188,
+      "loss": 0.36,
+      "step": 615
+    },
+    {
+      "epoch": 0.5417212756662297,
+      "grad_norm": 1.5508995056152344,
+      "learning_rate": 0.00019444847876391844,
+      "loss": 0.3682,
+      "step": 620
+    },
+    {
+      "epoch": 0.54608999563128,
+      "grad_norm": 2.227889060974121,
+      "learning_rate": 0.00019435781709547305,
+      "loss": 0.3889,
+      "step": 625
+    },
+    {
+      "epoch": 0.5504587155963303,
+      "grad_norm": 0.9221494197845459,
+      "learning_rate": 0.0001942664425987882,
+      "loss": 0.3375,
+      "step": 630
+    },
+    {
+      "epoch": 0.5548274355613805,
+      "grad_norm": 1.3386973142623901,
+      "learning_rate": 0.00019417435596415458,
+      "loss": 0.4833,
+      "step": 635
+    },
+    {
+      "epoch": 0.5591961555264308,
+      "grad_norm": 1.9686752557754517,
+      "learning_rate": 0.00019408155788724272,
+      "loss": 0.4739,
+      "step": 640
+    },
+    {
+      "epoch": 0.563564875491481,
+      "grad_norm": 2.3978073596954346,
+      "learning_rate": 0.00019398804906909777,
+      "loss": 0.4681,
+      "step": 645
+    },
+    {
+      "epoch": 0.5679335954565312,
+      "grad_norm": 1.536699652671814,
+      "learning_rate": 0.0001938938302161342,
+      "loss": 0.2684,
+      "step": 650
+    },
+    {
+      "epoch": 0.5723023154215815,
+      "grad_norm": 1.691787600517273,
+      "learning_rate": 0.00019379890204013043,
+      "loss": 0.3512,
+      "step": 655
+    },
+    {
+      "epoch": 0.5766710353866317,
+      "grad_norm": 1.7557870149612427,
+      "learning_rate": 0.0001937032652582235,
+      "loss": 0.3423,
+      "step": 660
+    },
+    {
+      "epoch": 0.581039755351682,
+      "grad_norm": 1.7950220108032227,
+      "learning_rate": 0.0001936069205929036,
+      "loss": 0.2831,
+      "step": 665
+    },
+    {
+      "epoch": 0.5854084753167322,
+      "grad_norm": 1.928232192993164,
+      "learning_rate": 0.00019350986877200867,
+      "loss": 0.323,
+      "step": 670
+    },
+    {
+      "epoch": 0.5897771952817824,
+      "grad_norm": 1.86429762840271,
+      "learning_rate": 0.00019341211052871887,
+      "loss": 0.4248,
+      "step": 675
+    },
+    {
+      "epoch": 0.5941459152468327,
+      "grad_norm": 2.022738456726074,
+      "learning_rate": 0.00019331364660155103,
+      "loss": 0.3411,
+      "step": 680
+    },
+    {
+      "epoch": 0.598514635211883,
+      "grad_norm": 1.2337995767593384,
+      "learning_rate": 0.00019321447773435306,
+      "loss": 0.2368,
+      "step": 685
+    },
+    {
+      "epoch": 0.6028833551769331,
+      "grad_norm": 2.015075445175171,
+      "learning_rate": 0.00019311460467629843,
+      "loss": 0.5116,
+      "step": 690
+    },
+    {
+      "epoch": 0.6072520751419834,
+      "grad_norm": 1.2344030141830444,
+      "learning_rate": 0.00019301402818188036,
+      "loss": 0.3313,
+      "step": 695
+    },
+    {
+      "epoch": 0.6116207951070336,
+      "grad_norm": 1.129764437675476,
+      "learning_rate": 0.00019291274901090625,
+      "loss": 0.408,
+      "step": 700
+    },
+    {
+      "epoch": 0.6159895150720839,
+      "grad_norm": 1.4350385665893555,
+      "learning_rate": 0.00019281076792849184,
+      "loss": 0.3729,
+      "step": 705
+    },
+    {
+      "epoch": 0.6203582350371342,
+      "grad_norm": 1.9586119651794434,
+      "learning_rate": 0.00019270808570505553,
+      "loss": 0.4315,
+      "step": 710
+    },
+    {
+      "epoch": 0.6247269550021843,
+      "grad_norm": 1.0157238245010376,
+      "learning_rate": 0.00019260470311631243,
+      "loss": 0.2861,
+      "step": 715
+    },
+    {
+      "epoch": 0.6290956749672346,
+      "grad_norm": 1.3841652870178223,
+      "learning_rate": 0.00019250062094326864,
+      "loss": 0.4037,
+      "step": 720
+    },
+    {
+      "epoch": 0.6334643949322848,
+      "grad_norm": 1.848821997642517,
+      "learning_rate": 0.00019239583997221525,
+      "loss": 0.3665,
+      "step": 725
+    },
+    {
+      "epoch": 0.6378331148973351,
+      "grad_norm": 0.9416481256484985,
+      "learning_rate": 0.0001922903609947225,
+      "loss": 0.339,
+      "step": 730
+    },
+    {
+      "epoch": 0.6422018348623854,
+      "grad_norm": 1.0696804523468018,
+      "learning_rate": 0.0001921841848076336,
+      "loss": 0.2783,
+      "step": 735
+    },
+    {
+      "epoch": 0.6465705548274355,
+      "grad_norm": 1.9199622869491577,
+      "learning_rate": 0.00019207731221305903,
+      "loss": 0.2904,
+      "step": 740
+    },
+    {
+      "epoch": 0.6509392747924858,
+      "grad_norm": 1.347430944442749,
+      "learning_rate": 0.00019196974401837008,
+      "loss": 0.2719,
+      "step": 745
+    },
+    {
+      "epoch": 0.6553079947575361,
+      "grad_norm": 0.9743670225143433,
+      "learning_rate": 0.0001918614810361932,
+      "loss": 0.2748,
+      "step": 750
+    },
+    {
+      "epoch": 0.6596767147225863,
+      "grad_norm": 1.4043099880218506,
+      "learning_rate": 0.00019175252408440343,
+      "loss": 0.3285,
+      "step": 755
+    },
+    {
+      "epoch": 0.6640454346876365,
+      "grad_norm": 2.9343338012695312,
+      "learning_rate": 0.0001916428739861185,
+      "loss": 0.4962,
+      "step": 760
+    },
+    {
+      "epoch": 0.6684141546526867,
+      "grad_norm": 2.3201515674591064,
+      "learning_rate": 0.0001915325315696926,
+      "loss": 0.3243,
+      "step": 765
+    },
+    {
+      "epoch": 0.672782874617737,
+      "grad_norm": 1.675564169883728,
+      "learning_rate": 0.00019142149766870992,
+      "loss": 0.4596,
+      "step": 770
+    },
+    {
+      "epoch": 0.6771515945827873,
+      "grad_norm": 1.664604663848877,
+      "learning_rate": 0.00019130977312197854,
+      "loss": 0.3024,
+      "step": 775
+    },
+    {
+      "epoch": 0.6815203145478375,
+      "grad_norm": 1.8358148336410522,
+      "learning_rate": 0.00019119735877352412,
+      "loss": 0.3862,
+      "step": 780
+    },
+    {
+      "epoch": 0.6858890345128877,
+      "grad_norm": 1.3632128238677979,
+      "learning_rate": 0.00019108425547258328,
+      "loss": 0.2374,
+      "step": 785
+    },
+    {
+      "epoch": 0.6902577544779379,
+      "grad_norm": 2.0279934406280518,
+      "learning_rate": 0.0001909704640735975,
+      "loss": 0.4392,
+      "step": 790
+    },
+    {
+      "epoch": 0.6946264744429882,
+      "grad_norm": 1.2824902534484863,
+      "learning_rate": 0.0001908559854362064,
+      "loss": 0.2782,
+      "step": 795
+    },
+    {
+      "epoch": 0.6989951944080385,
+      "grad_norm": 1.3477047681808472,
+      "learning_rate": 0.00019074082042524145,
+      "loss": 0.3631,
+      "step": 800
+    },
+    {
+      "epoch": 0.7033639143730887,
+      "grad_norm": 1.8478046655654907,
+      "learning_rate": 0.00019062496991071928,
+      "loss": 0.3788,
+      "step": 805
+    },
+    {
+      "epoch": 0.7077326343381389,
+      "grad_norm": 1.470382571220398,
+      "learning_rate": 0.0001905084347678352,
+      "loss": 0.3825,
+      "step": 810
+    },
+    {
+      "epoch": 0.7121013543031892,
+      "grad_norm": 2.4951813220977783,
+      "learning_rate": 0.00019039121587695652,
+      "loss": 0.3359,
+      "step": 815
+    },
+    {
+      "epoch": 0.7164700742682394,
+      "grad_norm": 2.3441359996795654,
+      "learning_rate": 0.000190273314123616,
+      "loss": 0.32,
+      "step": 820
+    },
+    {
+      "epoch": 0.7208387942332897,
+      "grad_norm": 2.372884750366211,
+      "learning_rate": 0.00019015473039850513,
+      "loss": 0.3651,
+      "step": 825
+    },
+    {
+      "epoch": 0.7252075141983398,
+      "grad_norm": 2.4474101066589355,
+      "learning_rate": 0.0001900354655974672,
+      "loss": 0.4401,
+      "step": 830
+    },
+    {
+      "epoch": 0.7295762341633901,
+      "grad_norm": 1.4031054973602295,
+      "learning_rate": 0.0001899155206214909,
+      "loss": 0.308,
+      "step": 835
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 1.6008141040802002,
+      "learning_rate": 0.00018979489637670322,
+      "loss": 0.2937,
+      "step": 840
+    },
+    {
+      "epoch": 0.7383136740934906,
+      "grad_norm": 0.9202178120613098,
+      "learning_rate": 0.0001896735937743627,
+      "loss": 0.3157,
+      "step": 845
+    },
+    {
+      "epoch": 0.7426823940585409,
+      "grad_norm": 1.024746298789978,
+      "learning_rate": 0.00018955161373085253,
+      "loss": 0.2934,
+      "step": 850
+    },
+    {
+      "epoch": 0.747051114023591,
+      "grad_norm": 1.1573566198349,
+      "learning_rate": 0.00018942895716767374,
+      "loss": 0.3617,
+      "step": 855
+    },
+    {
+      "epoch": 0.7514198339886413,
+      "grad_norm": 1.227409839630127,
+      "learning_rate": 0.00018930562501143805,
+      "loss": 0.3581,
+      "step": 860
+    },
+    {
+      "epoch": 0.7557885539536916,
+      "grad_norm": 1.5460100173950195,
+      "learning_rate": 0.00018918161819386095,
+      "loss": 0.3393,
+      "step": 865
+    },
+    {
+      "epoch": 0.7601572739187418,
+      "grad_norm": 1.688852310180664,
+      "learning_rate": 0.0001890569376517548,
+      "loss": 0.4389,
+      "step": 870
+    },
+    {
+      "epoch": 0.764525993883792,
+      "grad_norm": 1.5271598100662231,
+      "learning_rate": 0.00018893158432702149,
+      "loss": 0.2915,
+      "step": 875
+    },
+    {
+      "epoch": 0.7688947138488423,
+      "grad_norm": 1.695788860321045,
+      "learning_rate": 0.00018880555916664555,
+      "loss": 0.4026,
+      "step": 880
+    },
+    {
+      "epoch": 0.7732634338138925,
+      "grad_norm": 1.6879792213439941,
+      "learning_rate": 0.00018867886312268683,
+      "loss": 0.2857,
+      "step": 885
+    },
+    {
+      "epoch": 0.7776321537789428,
+      "grad_norm": 2.0718719959259033,
+      "learning_rate": 0.00018855149715227344,
+      "loss": 0.4236,
+      "step": 890
+    },
+    {
+      "epoch": 0.782000873743993,
+      "grad_norm": 1.5112775564193726,
+      "learning_rate": 0.00018842346221759448,
+      "loss": 0.325,
+      "step": 895
+    },
+    {
+      "epoch": 0.7863695937090432,
+      "grad_norm": 1.2844749689102173,
+      "learning_rate": 0.00018829475928589271,
+      "loss": 0.3782,
+      "step": 900
+    },
+    {
+      "epoch": 0.7907383136740935,
+      "grad_norm": 2.150299072265625,
+      "learning_rate": 0.00018816538932945728,
+      "loss": 0.3726,
+      "step": 905
+    },
+    {
+      "epoch": 0.7951070336391437,
+      "grad_norm": 1.7050650119781494,
+      "learning_rate": 0.00018803535332561646,
+      "loss": 0.3824,
+      "step": 910
+    },
+    {
+      "epoch": 0.799475753604194,
+      "grad_norm": 1.8164982795715332,
+      "learning_rate": 0.00018790465225673012,
+      "loss": 0.3664,
+      "step": 915
+    },
+    {
+      "epoch": 0.8038444735692443,
+      "grad_norm": 1.1102941036224365,
+      "learning_rate": 0.00018777328711018244,
+      "loss": 0.3166,
+      "step": 920
+    },
+    {
+      "epoch": 0.8082131935342944,
+      "grad_norm": 1.4220764636993408,
+      "learning_rate": 0.0001876412588783743,
+      "loss": 0.3049,
+      "step": 925
+    },
+    {
+      "epoch": 0.8125819134993447,
+      "grad_norm": 2.11336088180542,
+      "learning_rate": 0.000187508568558716,
+      "loss": 0.3076,
+      "step": 930
+    },
+    {
+      "epoch": 0.8169506334643949,
+      "grad_norm": 1.9948710203170776,
+      "learning_rate": 0.00018737521715361948,
+      "loss": 0.3846,
+      "step": 935
+    },
+    {
+      "epoch": 0.8213193534294452,
+      "grad_norm": 1.8913676738739014,
+      "learning_rate": 0.00018724120567049094,
+      "loss": 0.4296,
+      "step": 940
+    },
+    {
+      "epoch": 0.8256880733944955,
+      "grad_norm": 1.3633447885513306,
+      "learning_rate": 0.0001871065351217231,
+      "loss": 0.3569,
+      "step": 945
+    },
+    {
+      "epoch": 0.8300567933595456,
+      "grad_norm": 1.4957417249679565,
+      "learning_rate": 0.00018697120652468762,
+      "loss": 0.3085,
+      "step": 950
+    },
+    {
+      "epoch": 0.8344255133245959,
+      "grad_norm": 2.076399803161621,
+      "learning_rate": 0.0001868352209017275,
+      "loss": 0.3331,
+      "step": 955
+    },
+    {
+      "epoch": 0.8387942332896461,
+      "grad_norm": 1.1817855834960938,
+      "learning_rate": 0.00018669857928014906,
+      "loss": 0.3414,
+      "step": 960
+    },
+    {
+      "epoch": 0.8431629532546964,
+      "grad_norm": 1.4255414009094238,
+      "learning_rate": 0.00018656128269221454,
+      "loss": 0.2782,
+      "step": 965
+    },
+    {
+      "epoch": 0.8475316732197467,
+      "grad_norm": 1.326687216758728,
+      "learning_rate": 0.0001864233321751341,
+      "loss": 0.2998,
+      "step": 970
+    },
+    {
+      "epoch": 0.8519003931847968,
+      "grad_norm": 2.222280263900757,
+      "learning_rate": 0.00018628472877105793,
+      "loss": 0.3348,
+      "step": 975
+    },
+    {
+      "epoch": 0.8562691131498471,
+      "grad_norm": 1.518401026725769,
+      "learning_rate": 0.00018614547352706863,
+      "loss": 0.3816,
+      "step": 980
+    },
+    {
+      "epoch": 0.8606378331148974,
+      "grad_norm": 1.1030207872390747,
+      "learning_rate": 0.00018600556749517305,
+      "loss": 0.3222,
+      "step": 985
+    },
+    {
+      "epoch": 0.8650065530799476,
+      "grad_norm": 2.406994104385376,
+      "learning_rate": 0.00018586501173229437,
+      "loss": 0.3754,
+      "step": 990
+    },
+    {
+      "epoch": 0.8693752730449978,
+      "grad_norm": 1.2401646375656128,
+      "learning_rate": 0.00018572380730026434,
+      "loss": 0.4402,
+      "step": 995
+    },
+    {
+      "epoch": 0.873743993010048,
+      "grad_norm": 2.0233402252197266,
+      "learning_rate": 0.0001855819552658149,
+      "loss": 0.3323,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8781127129750983,
+      "grad_norm": 1.5329450368881226,
+      "learning_rate": 0.00018543945670057045,
+      "loss": 0.235,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8824814329401486,
+      "grad_norm": 1.8849459886550903,
+      "learning_rate": 0.00018529631268103964,
+      "loss": 0.357,
+      "step": 1010
+    },
+    {
+      "epoch": 0.8868501529051988,
+      "grad_norm": 2.016646146774292,
+      "learning_rate": 0.0001851525242886071,
+      "loss": 0.2663,
+      "step": 1015
+    },
+    {
+      "epoch": 0.891218872870249,
+      "grad_norm": 2.3272440433502197,
+      "learning_rate": 0.0001850080926095255,
+      "loss": 0.2926,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8955875928352992,
+      "grad_norm": 1.7760261297225952,
+      "learning_rate": 0.00018486301873490713,
+      "loss": 0.4155,
+      "step": 1025
+    },
+    {
+      "epoch": 0.8999563128003495,
+      "grad_norm": 1.4679979085922241,
+      "learning_rate": 0.0001847173037607159,
+      "loss": 0.2877,
+      "step": 1030
+    },
+    {
+      "epoch": 0.9043250327653998,
+      "grad_norm": 1.8398054838180542,
+      "learning_rate": 0.0001845709487877588,
+      "loss": 0.2856,
+      "step": 1035
+    },
+    {
+      "epoch": 0.9086937527304499,
+      "grad_norm": 3.05880069732666,
+      "learning_rate": 0.00018442395492167775,
+      "loss": 0.3373,
+      "step": 1040
+    },
+    {
+      "epoch": 0.9130624726955002,
+      "grad_norm": 1.2527328729629517,
+      "learning_rate": 0.0001842763232729412,
+      "loss": 0.2412,
+      "step": 1045
+    },
+    {
+      "epoch": 0.9174311926605505,
+      "grad_norm": 1.7745814323425293,
+      "learning_rate": 0.00018412805495683575,
+      "loss": 0.3955,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9217999126256007,
+      "grad_norm": 3.2864468097686768,
+      "learning_rate": 0.0001839791510934577,
+      "loss": 0.333,
+      "step": 1055
+    },
+    {
+      "epoch": 0.926168632590651,
+      "grad_norm": 2.0274927616119385,
+      "learning_rate": 0.0001838296128077046,
+      "loss": 0.4004,
+      "step": 1060
+    },
+    {
+      "epoch": 0.9305373525557011,
+      "grad_norm": 1.9851633310317993,
+      "learning_rate": 0.0001836794412292668,
+      "loss": 0.3132,
+      "step": 1065
+    },
+    {
+      "epoch": 0.9349060725207514,
+      "grad_norm": 1.3309999704360962,
+      "learning_rate": 0.00018352863749261883,
+      "loss": 0.2645,
+      "step": 1070
+    },
+    {
+      "epoch": 0.9392747924858017,
+      "grad_norm": 2.0173072814941406,
+      "learning_rate": 0.00018337720273701088,
+      "loss": 0.4376,
+      "step": 1075
+    },
+    {
+      "epoch": 0.9436435124508519,
+      "grad_norm": 1.815408706665039,
+      "learning_rate": 0.00018322513810646024,
+      "loss": 0.2851,
+      "step": 1080
+    },
+    {
+      "epoch": 0.9480122324159022,
+      "grad_norm": 1.1190584897994995,
+      "learning_rate": 0.00018307244474974254,
+      "loss": 0.4664,
+      "step": 1085
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.9746566414833069,
+      "learning_rate": 0.00018291912382038317,
+      "loss": 0.3816,
+      "step": 1090
+    },
+    {
+      "epoch": 0.9567496723460026,
+      "grad_norm": 1.9062715768814087,
+      "learning_rate": 0.0001827651764766485,
+      "loss": 0.3031,
+      "step": 1095
+    },
+    {
+      "epoch": 0.9611183923110529,
+      "grad_norm": 1.027502417564392,
+      "learning_rate": 0.00018261060388153718,
+      "loss": 0.2657,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5725,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 534084911751168.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:629a35960f565450f5c9e65334fb9c14eb136182b8af4bc22c885bdde32de5f3
+size 5777

checkpoint-1200/README.md

@@ -0,0 +1,207 @@
+---
+base_model: unsloth/functiongemma-270m-it
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/functiongemma-270m-it
+- lora
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1200/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/functiongemma-270m-it",
+  "bias": "none",
+  "corda_config": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}