Upload nixagent model

.gitattributes

@@ -33,3 +33,5 @@ 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-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,63 @@
----
-license: mit
----
+---
+base_model: unsloth/NVIDIA-Nemotron-3-Nano-4B
+library_name: peft
+model_name: unsloth_NVIDIA-Nemotron-3-Nano-4B_1774856196
+tags:
+- base_model:adapter:unsloth/NVIDIA-Nemotron-3-Nano-4B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for unsloth_NVIDIA-Nemotron-3-Nano-4B_1774856196
+
+This model is a fine-tuned version of [unsloth/NVIDIA-Nemotron-3-Nano-4B](https://huggingface.co/unsloth/NVIDIA-Nemotron-3-Nano-4B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.23.1
+- Transformers: 5.3.0
+- Pytorch: 2.10.0+cu130
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,51 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "NemotronHForCausalLM",
+    "parent_library": "transformers_modules.unsloth.NVIDIA_hyphen_Nemotron_hyphen_3_hyphen_Nano_hyphen_4B.b604b1379531cfac85a3cb195c387cc698aabdeb.modeling_nemotron_h",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "unsloth_training_method": "lora"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838ec41ee3b7dc900701126bac3d0e60bbb588914b5eccdfb16e12f45d8f9c9
+size 40490208

chat_template.jinja

@@ -0,0 +1,204 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson ) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{# Recompute last_user_idx relative to loop_messages after handling system #}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\n" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "\n\n" }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '\n<enum>' ~ (param_fields.enum | tojson ) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '\n<required>' ~ (tool.parameters.required | tojson ) ~ '</required>' }}
+        {%- endif %}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+
+
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {# Add reasoning content in to content field for unified processing below. #}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>\n" ~ message.reasoning_content ~ "\n</think>\n" ~ (message.content | default('', true)) %}
+        {%- else %}
+            {%- set content = message.content | default('', true) %}
+            {%- if content is string -%}
+                {# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
+                {%- if '<think>' not in content and '</think>' not in content -%}
+                    {%- set content = "<think></think>" ~ content -%}
+                {%- endif -%}
+            {%- else -%}
+                {%- set content = content -%}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {# Assistant message has tool calls. #}
+            {{- '<|im_start|>assistant\n' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '\n' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {# Keep only content after the last closing think. Also generation prompt causes this. #}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {# If <think> was opened but never closed, drop the trailing think segment #}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c | trim %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '\n' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>\n' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '\n</parameter>\n' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>\n</tool_call>\n' -}}
+                {%- endfor %}
+                {{- '<|im_end|>\n' }}
+        {%- else %}
+            {# Assistant message doesn't have tool calls. #}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant\n<|im_end|>\n' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set content = message.content | string %}
+        {{- content }}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think></think>' }}
+    {%- endif %}
+{%- endif %}

checkpoint-30/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/NVIDIA-Nemotron-3-Nano-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/NVIDIA-Nemotron-3-Nano-4B
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-30/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "NemotronHForCausalLM",
+    "parent_library": "transformers_modules.unsloth.NVIDIA_hyphen_Nemotron_hyphen_3_hyphen_Nano_hyphen_4B.b604b1379531cfac85a3cb195c387cc698aabdeb.modeling_nemotron_h",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/NVIDIA-Nemotron-3-Nano-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-30/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838ec41ee3b7dc900701126bac3d0e60bbb588914b5eccdfb16e12f45d8f9c9
+size 40490208

checkpoint-30/chat_template.jinja

@@ -0,0 +1,204 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson ) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+{%- set enable_thinking = enable_thinking if enable_thinking is defined else True %}
+{%- set truncate_history_thinking = truncate_history_thinking if truncate_history_thinking is defined else True %}
+
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- set loop_messages = messages %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+{# Recompute last_user_idx relative to loop_messages after handling system #}
+{%- set ns = namespace(last_user_idx = -1) %}
+{%- for m in loop_messages %}
+  {%- if m["role"] == "user" %}
+    {%- set ns.last_user_idx = loop.index0 %}
+  {%- endif %}
+{%- endfor %}
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\n" }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {%- if system_message is defined and system_message | length > 0 %}
+        {{- "\n\n" }}
+    {%- endif %}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- if param_fields.enum is defined %}
+                    {{- '\n<enum>' ~ (param_fields.enum | tojson ) ~ '</enum>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description', 'enum'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties', 'required'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {%- if tool.parameters is defined and tool.parameters.required is defined %}
+            {{- '\n<required>' ~ (tool.parameters.required | tojson ) ~ '</required>' }}
+        {%- endif %}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+
+
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" %}
+        {# Add reasoning content in to content field for unified processing below. #}
+        {%- if message.reasoning_content is defined and message.reasoning_content is string and message.reasoning_content | trim | length > 0 %}
+            {%- set content = "<think>\n" ~ message.reasoning_content ~ "\n</think>\n" ~ (message.content | default('', true)) %}
+        {%- else %}
+            {%- set content = message.content | default('', true) %}
+            {%- if content is string -%}
+                {# Allow downstream logic to to take care of broken thought, only handle coherent reasoning here. #}
+                {%- if '<think>' not in content and '</think>' not in content -%}
+                    {%- set content = "<think></think>" ~ content -%}
+                {%- endif -%}
+            {%- else -%}
+                {%- set content = content -%}
+            {%- endif -%}
+        {%- endif %}
+        {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+            {# Assistant message has tool calls. #}
+            {{- '<|im_start|>assistant\n' }}
+                {%- set include_content = not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {%- if content is string and content | trim | length > 0 %}
+                    {%- if include_content %}
+                        {{- (content | trim) ~ '\n' -}}
+                    {%- else %}
+                        {%- set c = (content | string) %}
+                        {%- if '</think>' in c %}
+                            {# Keep only content after the last closing think. Also generation prompt causes this. #}
+                            {%- set c = c.split('</think>')[-1] %}
+                        {%- elif '<think>' in c %}
+                            {# If <think> was opened but never closed, drop the trailing think segment #}
+                            {%- set c = c.split('<think>')[0] %}
+                        {%- endif %}
+                        {%- set c = "<think></think>" ~ c | trim %}
+                        {%- if c | length > 0 %}
+                            {{- c ~ '\n' -}}
+                        {%- endif %}
+                    {%- endif %}
+                {%- else %}
+                    {{- "<think></think>" -}}
+                {%- endif %}
+                {%- for tool_call in message.tool_calls %}
+                    {%- if tool_call.function is defined %}
+                        {%- set tool_call = tool_call.function %}
+                    {%- endif %}
+                    {{- '<tool_call>\n<function=' ~ tool_call.name ~ '>\n' -}}
+                        {%- if tool_call.arguments is defined %}
+                            {%- for args_name, args_value in tool_call.arguments|items %}
+                                {{- '<parameter=' ~ args_name ~ '>\n' -}}
+                                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                                {{- args_value ~ '\n</parameter>\n' -}}
+                            {%- endfor %}
+                        {%- endif %}
+                    {{- '</function>\n</tool_call>\n' -}}
+                {%- endfor %}
+                {{- '<|im_end|>\n' }}
+        {%- else %}
+            {# Assistant message doesn't have tool calls. #}
+            {%- if not (truncate_history_thinking and loop.index0 < ns.last_user_idx) %}
+                {{- '<|im_start|>assistant\n' ~ (content | default('', true) | string | trim) ~ '<|im_end|>\n' }}
+            {%- else %}
+                {%- set c = (content | default('', true) | string) %}
+                {%- if '<think>' in c and '</think>' in c %}
+                    {%- set c = "<think></think>" ~ c.split('</think>')[-1] %}
+                {%- endif %}
+                {%- set c = c | trim %}
+                {%- if c | length > 0 %}
+                    {{- '<|im_start|>assistant\n' ~ c ~ '<|im_end|>\n' }}
+                {%- else %}
+                    {{- '<|im_start|>assistant\n<|im_end|>\n' }}
+                {%- endif %}
+            {%- endif %}
+        {%- endif %}
+    {%- elif message.role == "user" or message.role == "system" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- set content = message.content | string %}
+        {{- content }}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+
+{%- if add_generation_prompt %}
+    {%- if enable_thinking %}
+        {{- '<|im_start|>assistant\n<think>\n' }}
+    {%- else %}
+        {{- '<|im_start|>assistant\n<think></think>' }}
+    {%- endif %}
+{%- endif %}

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9356e695fa000ff46944a7ba7d61d32ab1851bb16c69ea31e5b36fc0aac8a23
+size 20676171

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b45f84e4a65f770909a2acffd69867eb689ece81377b628d95f68d63d41bff
+size 14645

checkpoint-30/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dccf17fff2acdcc8fb3349f377136fb981b58a0c777eeef5d6160b3aae41e52
+size 1383

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d65250290ca0ba47d76797cfae41bed809ba7a96636352bff487b24f05f6231
+size 1465

checkpoint-30/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484

checkpoint-30/tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 262144,
+  "pad_token": "<SPECIAL_999>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

checkpoint-30/trainer_state.json

@@ -0,0 +1,424 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05937654626422563,
+  "eval_steps": 3,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0019792182088075212,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 8.076898574829102,
+      "num_input_tokens_seen": 2942,
+      "step": 1,
+      "train_runtime": 697.1739,
+      "train_tokens_per_second": 4.22
+    },
+    {
+      "epoch": 0.0039584364176150424,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 6.006780624389648,
+      "num_input_tokens_seen": 8009,
+      "step": 2,
+      "train_runtime": 724.0489,
+      "train_tokens_per_second": 11.061
+    },
+    {
+      "epoch": 0.005937654626422563,
+      "grad_norm": 0.33343738317489624,
+      "learning_rate": 0.0,
+      "loss": 9.303730964660645,
+      "num_input_tokens_seen": 9957,
+      "step": 3,
+      "train_runtime": 729.6177,
+      "train_tokens_per_second": 13.647
+    },
+    {
+      "epoch": 0.005937654626422563,
+      "eval_loss": 1.6509373188018799,
+      "eval_runtime": 39.0128,
+      "eval_samples_per_second": 3.281,
+      "eval_steps_per_second": 0.82,
+      "num_input_tokens_seen": 9957,
+      "step": 3
+    },
+    {
+      "epoch": 0.007916872835230085,
+      "grad_norm": 0.35222020745277405,
+      "learning_rate": 1e-05,
+      "loss": 8.339298248291016,
+      "num_input_tokens_seen": 12579,
+      "step": 4,
+      "train_runtime": 775.7485,
+      "train_tokens_per_second": 16.215
+    },
+    {
+      "epoch": 0.009896091044037604,
+      "grad_norm": 0.4923153519630432,
+      "learning_rate": 2e-05,
+      "loss": 5.858340263366699,
+      "num_input_tokens_seen": 18548,
+      "step": 5,
+      "train_runtime": 791.4629,
+      "train_tokens_per_second": 23.435
+    },
+    {
+      "epoch": 0.011875309252845126,
+      "grad_norm": 0.4596147835254669,
+      "learning_rate": 3e-05,
+      "loss": 7.152117729187012,
+      "num_input_tokens_seen": 22715,
+      "step": 6,
+      "train_runtime": 802.7905,
+      "train_tokens_per_second": 28.295
+    },
+    {
+      "epoch": 0.011875309252845126,
+      "eval_loss": 1.6447160243988037,
+      "eval_runtime": 38.6774,
+      "eval_samples_per_second": 3.309,
+      "eval_steps_per_second": 0.827,
+      "num_input_tokens_seen": 22715,
+      "step": 6
+    },
+    {
+      "epoch": 0.013854527461652647,
+      "grad_norm": 0.4033356308937073,
+      "learning_rate": 4e-05,
+      "loss": 8.132979393005371,
+      "num_input_tokens_seen": 26012,
+      "step": 7,
+      "train_runtime": 850.5164,
+      "train_tokens_per_second": 30.584
+    },
+    {
+      "epoch": 0.01583374567046017,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 5.526519775390625,
+      "num_input_tokens_seen": 32601,
+      "step": 8,
+      "train_runtime": 867.4081,
+      "train_tokens_per_second": 37.584
+    },
+    {
+      "epoch": 0.017812963879267688,
+      "grad_norm": 0.4410555064678192,
+      "learning_rate": 5e-05,
+      "loss": 6.735212326049805,
+      "num_input_tokens_seen": 36772,
+      "step": 9,
+      "train_runtime": 878.5352,
+      "train_tokens_per_second": 41.856
+    },
+    {
+      "epoch": 0.017812963879267688,
+      "eval_loss": 1.6224464178085327,
+      "eval_runtime": 38.4019,
+      "eval_samples_per_second": 3.333,
+      "eval_steps_per_second": 0.833,
+      "num_input_tokens_seen": 36772,
+      "step": 9
+    },
+    {
+      "epoch": 0.01979218208807521,
+      "grad_norm": 0.41144317388534546,
+      "learning_rate": 4.8e-05,
+      "loss": 7.8381853103637695,
+      "num_input_tokens_seen": 41799,
+      "step": 10,
+      "train_runtime": 929.9841,
+      "train_tokens_per_second": 44.946
+    },
+    {
+      "epoch": 0.02177140029688273,
+      "grad_norm": 0.49192050099372864,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 8.786320686340332,
+      "num_input_tokens_seen": 44038,
+      "step": 11,
+      "train_runtime": 936.1529,
+      "train_tokens_per_second": 47.041
+    },
+    {
+      "epoch": 0.02375061850569025,
+      "grad_norm": 0.3306628465652466,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 8.384254455566406,
+      "num_input_tokens_seen": 46086,
+      "step": 12,
+      "train_runtime": 941.817,
+      "train_tokens_per_second": 48.933
+    },
+    {
+      "epoch": 0.02375061850569025,
+      "eval_loss": 1.5842628479003906,
+      "eval_runtime": 38.3991,
+      "eval_samples_per_second": 3.333,
+      "eval_steps_per_second": 0.833,
+      "num_input_tokens_seen": 46086,
+      "step": 12
+    },
+    {
+      "epoch": 0.025729836714497772,
+      "grad_norm": 0.4944745898246765,
+      "learning_rate": 4.2e-05,
+      "loss": 8.164417266845703,
+      "num_input_tokens_seen": 49507,
+      "step": 13,
+      "train_runtime": 989.3818,
+      "train_tokens_per_second": 50.038
+    },
+    {
+      "epoch": 0.027709054923305294,
+      "grad_norm": 0.3035735785961151,
+      "learning_rate": 4e-05,
+      "loss": 8.058252334594727,
+      "num_input_tokens_seen": 52233,
+      "step": 14,
+      "train_runtime": 996.6464,
+      "train_tokens_per_second": 52.409
+    },
+    {
+      "epoch": 0.029688273132112815,
+      "grad_norm": 0.33408379554748535,
+      "learning_rate": 3.8e-05,
+      "loss": 7.010341167449951,
+      "num_input_tokens_seen": 55234,
+      "step": 15,
+      "train_runtime": 1004.6341,
+      "train_tokens_per_second": 54.979
+    },
+    {
+      "epoch": 0.029688273132112815,
+      "eval_loss": 1.5526598691940308,
+      "eval_runtime": 38.2948,
+      "eval_samples_per_second": 3.342,
+      "eval_steps_per_second": 0.836,
+      "num_input_tokens_seen": 55234,
+      "step": 15
+    },
+    {
+      "epoch": 0.03166749134092034,
+      "grad_norm": 0.28500697016716003,
+      "learning_rate": 3.6e-05,
+      "loss": 7.41168737411499,
+      "num_input_tokens_seen": 58400,
+      "step": 16,
+      "train_runtime": 1051.3309,
+      "train_tokens_per_second": 55.549
+    },
+    {
+      "epoch": 0.03364670954972786,
+      "grad_norm": 0.5121440887451172,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 7.725010395050049,
+      "num_input_tokens_seen": 62169,
+      "step": 17,
+      "train_runtime": 1061.4008,
+      "train_tokens_per_second": 58.573
+    },
+    {
+      "epoch": 0.035625927758535375,
+      "grad_norm": 0.6245442628860474,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 6.330207347869873,
+      "num_input_tokens_seen": 66801,
+      "step": 18,
+      "train_runtime": 1073.4796,
+      "train_tokens_per_second": 62.228
+    },
+    {
+      "epoch": 0.035625927758535375,
+      "eval_loss": 1.5273845195770264,
+      "eval_runtime": 38.4036,
+      "eval_samples_per_second": 3.333,
+      "eval_steps_per_second": 0.833,
+      "num_input_tokens_seen": 66801,
+      "step": 18
+    },
+    {
+      "epoch": 0.0376051459673429,
+      "grad_norm": 0.3218696117401123,
+      "learning_rate": 3e-05,
+      "loss": 7.721973419189453,
+      "num_input_tokens_seen": 68693,
+      "step": 19,
+      "train_runtime": 1117.2758,
+      "train_tokens_per_second": 61.483
+    },
+    {
+      "epoch": 0.03958436417615042,
+      "grad_norm": 0.4316211938858032,
+      "learning_rate": 2.8000000000000003e-05,
+      "loss": 5.789700031280518,
+      "num_input_tokens_seen": 74505,
+      "step": 20,
+      "train_runtime": 1132.4346,
+      "train_tokens_per_second": 65.792
+    },
+    {
+      "epoch": 0.04156358238495794,
+      "grad_norm": 0.36192160844802856,
+      "learning_rate": 2.6000000000000002e-05,
+      "loss": 5.359489440917969,
+      "num_input_tokens_seen": 82017,
+      "step": 21,
+      "train_runtime": 1151.4895,
+      "train_tokens_per_second": 71.227
+    },
+    {
+      "epoch": 0.04156358238495794,
+      "eval_loss": 1.5085684061050415,
+      "eval_runtime": 38.2169,
+      "eval_samples_per_second": 3.349,
+      "eval_steps_per_second": 0.837,
+      "num_input_tokens_seen": 82017,
+      "step": 21
+    },
+    {
+      "epoch": 0.04354280059376546,
+      "grad_norm": 0.35479193925857544,
+      "learning_rate": 2.4e-05,
+      "loss": 7.415735244750977,
+      "num_input_tokens_seen": 84672,
+      "step": 22,
+      "train_runtime": 1197.1732,
+      "train_tokens_per_second": 70.727
+    },
+    {
+      "epoch": 0.045522018802572985,
+      "grad_norm": 0.3102089464664459,
+      "learning_rate": 2.2000000000000003e-05,
+      "loss": 5.640255928039551,
+      "num_input_tokens_seen": 88890,
+      "step": 23,
+      "train_runtime": 1208.5904,
+      "train_tokens_per_second": 73.548
+    },
+    {
+      "epoch": 0.0475012370113805,
+      "grad_norm": 0.31496089696884155,
+      "learning_rate": 2e-05,
+      "loss": 7.0548906326293945,
+      "num_input_tokens_seen": 92773,
+      "step": 24,
+      "train_runtime": 1218.7108,
+      "train_tokens_per_second": 76.124
+    },
+    {
+      "epoch": 0.0475012370113805,
+      "eval_loss": 1.495510220527649,
+      "eval_runtime": 38.2529,
+      "eval_samples_per_second": 3.346,
+      "eval_steps_per_second": 0.837,
+      "num_input_tokens_seen": 92773,
+      "step": 24
+    },
+    {
+      "epoch": 0.04948045522018803,
+      "grad_norm": 0.3281867206096649,
+      "learning_rate": 1.8e-05,
+      "loss": 7.233792304992676,
+      "num_input_tokens_seen": 95385,
+      "step": 25,
+      "train_runtime": 1263.8477,
+      "train_tokens_per_second": 75.472
+    },
+    {
+      "epoch": 0.051459673428995545,
+      "grad_norm": 0.3076775372028351,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 6.263100624084473,
+      "num_input_tokens_seen": 99968,
+      "step": 26,
+      "train_runtime": 1275.9673,
+      "train_tokens_per_second": 78.347
+    },
+    {
+      "epoch": 0.05343889163780307,
+      "grad_norm": 0.36238089203834534,
+      "learning_rate": 1.4000000000000001e-05,
+      "loss": 7.531805515289307,
+      "num_input_tokens_seen": 103394,
+      "step": 27,
+      "train_runtime": 1285.2238,
+      "train_tokens_per_second": 80.448
+    },
+    {
+      "epoch": 0.05343889163780307,
+      "eval_loss": 1.4868113994598389,
+      "eval_runtime": 38.2858,
+      "eval_samples_per_second": 3.343,
+      "eval_steps_per_second": 0.836,
+      "num_input_tokens_seen": 103394,
+      "step": 27
+    },
+    {
+      "epoch": 0.05541810984661059,
+      "grad_norm": 0.36287209391593933,
+      "learning_rate": 1.2e-05,
+      "loss": 7.41123104095459,
+      "num_input_tokens_seen": 107552,
+      "step": 28,
+      "train_runtime": 1334.3841,
+      "train_tokens_per_second": 80.6
+    },
+    {
+      "epoch": 0.05739732805541811,
+      "grad_norm": 0.33840489387512207,
+      "learning_rate": 1e-05,
+      "loss": 8.186224937438965,
+      "num_input_tokens_seen": 109305,
+      "step": 29,
+      "train_runtime": 1339.2503,
+      "train_tokens_per_second": 81.617
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "grad_norm": 0.29359596967697144,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 5.34782075881958,
+      "num_input_tokens_seen": 113042,
+      "step": 30,
+      "train_runtime": 1349.1236,
+      "train_tokens_per_second": 83.789
+    },
+    {
+      "epoch": 0.05937654626422563,
+      "eval_loss": 1.4815630912780762,
+      "eval_runtime": 38.3292,
+      "eval_samples_per_second": 3.339,
+      "eval_steps_per_second": 0.835,
+      "num_input_tokens_seen": 113042,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 30,
+  "num_input_tokens_seen": 113042,
+  "num_train_epochs": 1,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2423146296844416.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0a2e219055bcf0338a5e7c22916a5075c73e409a8b742172a43e58f559d246
+size 5777

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623c34567aebb18582765289fbe23d901c62704d6518d71866e0e58db892b5b7
+size 17077484

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 262144,
+  "pad_token": "<SPECIAL_999>",
+  "padding_side": "left",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc0a2e219055bcf0338a5e7c22916a5075c73e409a8b742172a43e58f559d246
+size 5777