LoRA fine-tune on AMD MI300X: Qwen2.5-7B ASD clinical interpreter

.gitattributes

@@ -33,3 +33,6 @@ 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-350/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-357/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: asd_interpreter_lora
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for asd_interpreter_lora
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+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 0.17.1
+- TRL: 0.21.0
+- Transformers: 4.55.0
+- Pytorch: 2.9.0.dev20250821+rocm7.0.0.lw.git125803b7
+- Datasets: 4.0.0
+- Tokenizers: 0.21.4
+
+## 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 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_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 sha256:938aa5d7e97fc980fca4e9c0aea1b28ca17910282636f50b95893405a3e47bb1
+size 161533192

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-350/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-350/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-350/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938aa5d7e97fc980fca4e9c0aea1b28ca17910282636f50b95893405a3e47bb1
+size 161533192

checkpoint-350/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-350/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-350/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41babdd82827746ced31bd32cd8635823060983690dce96fa43036b63570cf4f
+size 323291451

checkpoint-350/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54e584710f3593ca12e42834f7f8c887688fe790eb0d2db7916d75fedfaf890
+size 14645

checkpoint-350/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe68fbb306c3ac0423bd3cb71b3916fbd621d020bf98eb1ace05c98678b87718
+size 1465

checkpoint-350/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-350/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-350/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-350/trainer_state.json

@@ -0,0 +1,419 @@
+{
+  "best_global_step": 350,
+  "best_metric": 0.10404938459396362,
+  "best_model_checkpoint": "finetune_data/asd_interpreter_lora/checkpoint-350",
+  "epoch": 2.943157894736842,
+  "eval_steps": 50,
+  "global_step": 350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 1.0511218309402466,
+      "learning_rate": 0.0001,
+      "loss": 2.6112,
+      "mean_token_accuracy": 0.5126021690666676,
+      "num_tokens": 84675.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.9096640944480896,
+      "learning_rate": 0.00019999570594853575,
+      "loss": 1.2518,
+      "mean_token_accuracy": 0.6996544972062111,
+      "num_tokens": 164396.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 3.1940813064575195,
+      "learning_rate": 0.00019948086584424256,
+      "loss": 0.3253,
+      "mean_token_accuracy": 0.9035305514931679,
+      "num_tokens": 241947.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.4178029000759125,
+      "learning_rate": 0.0001981122789824607,
+      "loss": 0.2067,
+      "mean_token_accuracy": 0.9319008827209473,
+      "num_tokens": 326149.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.23984290659427643,
+      "learning_rate": 0.00019590169060269602,
+      "loss": 0.1369,
+      "mean_token_accuracy": 0.9472503453493119,
+      "num_tokens": 405814.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.12887074053287506,
+      "eval_mean_token_accuracy": 0.9501652488341699,
+      "eval_num_tokens": 405814.0,
+      "eval_runtime": 3.2571,
+      "eval_samples_per_second": 30.702,
+      "eval_steps_per_second": 3.991,
+      "step": 50
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.32201144099235535,
+      "learning_rate": 0.00019286807201812867,
+      "loss": 0.1211,
+      "mean_token_accuracy": 0.9524481907486916,
+      "num_tokens": 484365.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.1699223816394806,
+      "learning_rate": 0.00018903745780342839,
+      "loss": 0.1194,
+      "mean_token_accuracy": 0.9521158829331398,
+      "num_tokens": 568191.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.11287683993577957,
+      "learning_rate": 0.0001844427223655199,
+      "loss": 0.1133,
+      "mean_token_accuracy": 0.9534999072551728,
+      "num_tokens": 647422.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.16161221265792847,
+      "learning_rate": 0.00017912329781477287,
+      "loss": 0.1111,
+      "mean_token_accuracy": 0.9529792726039886,
+      "num_tokens": 726806.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.13746266067028046,
+      "learning_rate": 0.00017312483555785086,
+      "loss": 0.111,
+      "mean_token_accuracy": 0.9529147148132324,
+      "num_tokens": 809955.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.11152192950248718,
+      "eval_mean_token_accuracy": 0.952180761557359,
+      "eval_num_tokens": 809955.0,
+      "eval_runtime": 3.3115,
+      "eval_samples_per_second": 30.198,
+      "eval_steps_per_second": 3.926,
+      "step": 100
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1132306233048439,
+      "learning_rate": 0.00016649881451643705,
+      "loss": 0.109,
+      "mean_token_accuracy": 0.9546180069446564,
+      "num_tokens": 888974.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.0084210526315789,
+      "grad_norm": 0.15029756724834442,
+      "learning_rate": 0.00015930209933411036,
+      "loss": 0.1073,
+      "mean_token_accuracy": 0.954869093039097,
+      "num_tokens": 965339.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.0926315789473684,
+      "grad_norm": 0.09324247390031815,
+      "learning_rate": 0.0001515964523628501,
+      "loss": 0.1058,
+      "mean_token_accuracy": 0.9544935628771782,
+      "num_tokens": 1049239.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.176842105263158,
+      "grad_norm": 0.09921601414680481,
+      "learning_rate": 0.00014344800361731027,
+      "loss": 0.1066,
+      "mean_token_accuracy": 0.9543229445815087,
+      "num_tokens": 1128853.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.2610526315789474,
+      "grad_norm": 0.14502032101154327,
+      "learning_rate": 0.00013492668324572614,
+      "loss": 0.1057,
+      "mean_token_accuracy": 0.9546637967228889,
+      "num_tokens": 1207359.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.2610526315789474,
+      "eval_loss": 0.10642929375171661,
+      "eval_mean_token_accuracy": 0.9541201224693885,
+      "eval_num_tokens": 1207359.0,
+      "eval_runtime": 3.3561,
+      "eval_samples_per_second": 29.796,
+      "eval_steps_per_second": 3.873,
+      "step": 150
+    },
+    {
+      "epoch": 1.345263157894737,
+      "grad_norm": 0.07445153594017029,
+      "learning_rate": 0.00012610562138799978,
+      "loss": 0.1054,
+      "mean_token_accuracy": 0.9534011006355285,
+      "num_tokens": 1291078.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.4294736842105262,
+      "grad_norm": 0.0736021175980568,
+      "learning_rate": 0.00011706052057139335,
+      "loss": 0.1042,
+      "mean_token_accuracy": 0.9556787937879563,
+      "num_tokens": 1370250.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.5136842105263157,
+      "grad_norm": 0.10876885801553726,
+      "learning_rate": 0.00010786900602994359,
+      "loss": 0.1048,
+      "mean_token_accuracy": 0.9544201374053956,
+      "num_tokens": 1449612.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.5978947368421053,
+      "grad_norm": 0.10258373618125916,
+      "learning_rate": 9.860995952316851e-05,
+      "loss": 0.1035,
+      "mean_token_accuracy": 0.9549568623304368,
+      "num_tokens": 1532874.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.6821052631578948,
+      "grad_norm": 0.09369785338640213,
+      "learning_rate": 8.936284237124778e-05,
+      "loss": 0.1044,
+      "mean_token_accuracy": 0.9551588267087936,
+      "num_tokens": 1611823.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.6821052631578948,
+      "eval_loss": 0.10525871068239212,
+      "eval_mean_token_accuracy": 0.9543446852610662,
+      "eval_num_tokens": 1611823.0,
+      "eval_runtime": 3.4604,
+      "eval_samples_per_second": 28.899,
+      "eval_steps_per_second": 3.757,
+      "step": 200
+    },
+    {
+      "epoch": 1.7663157894736843,
+      "grad_norm": 0.09880904853343964,
+      "learning_rate": 8.020701351640182e-05,
+      "loss": 0.1045,
+      "mean_token_accuracy": 0.9547461196780205,
+      "num_tokens": 1692230.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.8505263157894736,
+      "grad_norm": 0.07497906684875488,
+      "learning_rate": 7.122104846288064e-05,
+      "loss": 0.1024,
+      "mean_token_accuracy": 0.9548232913017273,
+      "num_tokens": 1774458.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.9347368421052633,
+      "grad_norm": 0.09438126534223557,
+      "learning_rate": 6.248206494043313e-05,
+      "loss": 0.104,
+      "mean_token_accuracy": 0.9549880161881447,
+      "num_tokens": 1853023.0,
+      "step": 230
+    },
+    {
+      "epoch": 2.0168421052631578,
+      "grad_norm": 0.09313005208969116,
+      "learning_rate": 5.4065061078425315e-05,
+      "loss": 0.103,
+      "mean_token_accuracy": 0.9549200183305985,
+      "num_tokens": 1930647.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.1010526315789475,
+      "grad_norm": 0.07283347845077515,
+      "learning_rate": 4.604227177041156e-05,
+      "loss": 0.1019,
+      "mean_token_accuracy": 0.9548763617873192,
+      "num_tokens": 2014768.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.1010526315789475,
+      "eval_loss": 0.10490619391202927,
+      "eval_mean_token_accuracy": 0.9543710763637836,
+      "eval_num_tokens": 2014768.0,
+      "eval_runtime": 3.4547,
+      "eval_samples_per_second": 28.946,
+      "eval_steps_per_second": 3.763,
+      "step": 250
+    },
+    {
+      "epoch": 2.185263157894737,
+      "grad_norm": 0.0957074984908104,
+      "learning_rate": 3.848254875285e-05,
+      "loss": 0.103,
+      "mean_token_accuracy": 0.955729816854,
+      "num_tokens": 2094236.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.269473684210526,
+      "grad_norm": 0.08435027301311493,
+      "learning_rate": 3.145076971813891e-05,
+      "loss": 0.1027,
+      "mean_token_accuracy": 0.9557207286357879,
+      "num_tokens": 2173722.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.353684210526316,
+      "grad_norm": 0.07077847421169281,
+      "learning_rate": 2.500728153297788e-05,
+      "loss": 0.102,
+      "mean_token_accuracy": 0.9550597742199898,
+      "num_tokens": 2256619.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.437894736842105,
+      "grad_norm": 0.07486104220151901,
+      "learning_rate": 1.9207382340364634e-05,
+      "loss": 0.1024,
+      "mean_token_accuracy": 0.9555209368467331,
+      "num_tokens": 2335617.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.522105263157895,
+      "grad_norm": 0.06978271156549454,
+      "learning_rate": 1.41008469898387e-05,
+      "loss": 0.1031,
+      "mean_token_accuracy": 0.9553255036473274,
+      "num_tokens": 2415889.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.522105263157895,
+      "eval_loss": 0.10419522225856781,
+      "eval_mean_token_accuracy": 0.9541570269144498,
+      "eval_num_tokens": 2415889.0,
+      "eval_runtime": 3.5101,
+      "eval_samples_per_second": 28.489,
+      "eval_steps_per_second": 3.704,
+      "step": 300
+    },
+    {
+      "epoch": 2.606315789473684,
+      "grad_norm": 0.07363743335008621,
+      "learning_rate": 9.731499868738447e-06,
+      "loss": 0.1016,
+      "mean_token_accuracy": 0.9559778571128845,
+      "num_tokens": 2498011.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.690526315789474,
+      "grad_norm": 0.07047491520643234,
+      "learning_rate": 6.136838800442457e-06,
+      "loss": 0.1026,
+      "mean_token_accuracy": 0.9554199263453483,
+      "num_tokens": 2576551.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.774736842105263,
+      "grad_norm": 0.07501808553934097,
+      "learning_rate": 3.3477132373081254e-06,
+      "loss": 0.1014,
+      "mean_token_accuracy": 0.9564116463065148,
+      "num_tokens": 2657833.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.8589473684210525,
+      "grad_norm": 0.07335389405488968,
+      "learning_rate": 1.3880595100613792e-06,
+      "loss": 0.1023,
+      "mean_token_accuracy": 0.9557045891880989,
+      "num_tokens": 2739348.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.943157894736842,
+      "grad_norm": 0.06935805082321167,
+      "learning_rate": 2.746954057333606e-07,
+      "loss": 0.102,
+      "mean_token_accuracy": 0.956343337893486,
+      "num_tokens": 2817342.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.943157894736842,
+      "eval_loss": 0.10404938459396362,
+      "eval_mean_token_accuracy": 0.9544462653306814,
+      "eval_num_tokens": 2817342.0,
+      "eval_runtime": 3.5152,
+      "eval_samples_per_second": 28.448,
+      "eval_steps_per_second": 3.698,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 357,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2029728884607795e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-350/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c27b526db1ae1b28312267b5b3e8bcd79b6cbe86e77aeaa8334cf99438db39
+size 6097

checkpoint-357/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-357/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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": 32,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-357/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0cfa07a4107ac08a0df16007d2adc0a6c2df1280be19c67d9ef1fc2e3b21ed4
+size 161533192

checkpoint-357/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-357/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-357/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:507c83c19f228f4617d06654cc474dc6b5edb4adf00d916d2456caa1ce885985
+size 323291451

checkpoint-357/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3657157f4f292cf53695c7f2660ba3906347028b1019b3a53fbc1c831d154ca
+size 14645

checkpoint-357/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55abab1dc961a38dada7aee5e4633b39054589fcfd0101deb751914746cd7682
+size 1465

checkpoint-357/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

checkpoint-357/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

checkpoint-357/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-357/trainer_state.json

@@ -0,0 +1,419 @@
+{
+  "best_global_step": 350,
+  "best_metric": 0.10404938459396362,
+  "best_model_checkpoint": "finetune_data/asd_interpreter_lora/checkpoint-350",
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 357,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 1.0511218309402466,
+      "learning_rate": 0.0001,
+      "loss": 2.6112,
+      "mean_token_accuracy": 0.5126021690666676,
+      "num_tokens": 84675.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 0.9096640944480896,
+      "learning_rate": 0.00019999570594853575,
+      "loss": 1.2518,
+      "mean_token_accuracy": 0.6996544972062111,
+      "num_tokens": 164396.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.25263157894736843,
+      "grad_norm": 3.1940813064575195,
+      "learning_rate": 0.00019948086584424256,
+      "loss": 0.3253,
+      "mean_token_accuracy": 0.9035305514931679,
+      "num_tokens": 241947.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 0.4178029000759125,
+      "learning_rate": 0.0001981122789824607,
+      "loss": 0.2067,
+      "mean_token_accuracy": 0.9319008827209473,
+      "num_tokens": 326149.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.23984290659427643,
+      "learning_rate": 0.00019590169060269602,
+      "loss": 0.1369,
+      "mean_token_accuracy": 0.9472503453493119,
+      "num_tokens": 405814.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.12887074053287506,
+      "eval_mean_token_accuracy": 0.9501652488341699,
+      "eval_num_tokens": 405814.0,
+      "eval_runtime": 3.2571,
+      "eval_samples_per_second": 30.702,
+      "eval_steps_per_second": 3.991,
+      "step": 50
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 0.32201144099235535,
+      "learning_rate": 0.00019286807201812867,
+      "loss": 0.1211,
+      "mean_token_accuracy": 0.9524481907486916,
+      "num_tokens": 484365.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.1699223816394806,
+      "learning_rate": 0.00018903745780342839,
+      "loss": 0.1194,
+      "mean_token_accuracy": 0.9521158829331398,
+      "num_tokens": 568191.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.11287683993577957,
+      "learning_rate": 0.0001844427223655199,
+      "loss": 0.1133,
+      "mean_token_accuracy": 0.9534999072551728,
+      "num_tokens": 647422.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.16161221265792847,
+      "learning_rate": 0.00017912329781477287,
+      "loss": 0.1111,
+      "mean_token_accuracy": 0.9529792726039886,
+      "num_tokens": 726806.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.13746266067028046,
+      "learning_rate": 0.00017312483555785086,
+      "loss": 0.111,
+      "mean_token_accuracy": 0.9529147148132324,
+      "num_tokens": 809955.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.11152192950248718,
+      "eval_mean_token_accuracy": 0.952180761557359,
+      "eval_num_tokens": 809955.0,
+      "eval_runtime": 3.3115,
+      "eval_samples_per_second": 30.198,
+      "eval_steps_per_second": 3.926,
+      "step": 100
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.1132306233048439,
+      "learning_rate": 0.00016649881451643705,
+      "loss": 0.109,
+      "mean_token_accuracy": 0.9546180069446564,
+      "num_tokens": 888974.0,
+      "step": 110
+    },
+    {
+      "epoch": 1.0084210526315789,
+      "grad_norm": 0.15029756724834442,
+      "learning_rate": 0.00015930209933411036,
+      "loss": 0.1073,
+      "mean_token_accuracy": 0.954869093039097,
+      "num_tokens": 965339.0,
+      "step": 120
+    },
+    {
+      "epoch": 1.0926315789473684,
+      "grad_norm": 0.09324247390031815,
+      "learning_rate": 0.0001515964523628501,
+      "loss": 0.1058,
+      "mean_token_accuracy": 0.9544935628771782,
+      "num_tokens": 1049239.0,
+      "step": 130
+    },
+    {
+      "epoch": 1.176842105263158,
+      "grad_norm": 0.09921601414680481,
+      "learning_rate": 0.00014344800361731027,
+      "loss": 0.1066,
+      "mean_token_accuracy": 0.9543229445815087,
+      "num_tokens": 1128853.0,
+      "step": 140
+    },
+    {
+      "epoch": 1.2610526315789474,
+      "grad_norm": 0.14502032101154327,
+      "learning_rate": 0.00013492668324572614,
+      "loss": 0.1057,
+      "mean_token_accuracy": 0.9546637967228889,
+      "num_tokens": 1207359.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.2610526315789474,
+      "eval_loss": 0.10642929375171661,
+      "eval_mean_token_accuracy": 0.9541201224693885,
+      "eval_num_tokens": 1207359.0,
+      "eval_runtime": 3.3561,
+      "eval_samples_per_second": 29.796,
+      "eval_steps_per_second": 3.873,
+      "step": 150
+    },
+    {
+      "epoch": 1.345263157894737,
+      "grad_norm": 0.07445153594017029,
+      "learning_rate": 0.00012610562138799978,
+      "loss": 0.1054,
+      "mean_token_accuracy": 0.9534011006355285,
+      "num_tokens": 1291078.0,
+      "step": 160
+    },
+    {
+      "epoch": 1.4294736842105262,
+      "grad_norm": 0.0736021175980568,
+      "learning_rate": 0.00011706052057139335,
+      "loss": 0.1042,
+      "mean_token_accuracy": 0.9556787937879563,
+      "num_tokens": 1370250.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.5136842105263157,
+      "grad_norm": 0.10876885801553726,
+      "learning_rate": 0.00010786900602994359,
+      "loss": 0.1048,
+      "mean_token_accuracy": 0.9544201374053956,
+      "num_tokens": 1449612.0,
+      "step": 180
+    },
+    {
+      "epoch": 1.5978947368421053,
+      "grad_norm": 0.10258373618125916,
+      "learning_rate": 9.860995952316851e-05,
+      "loss": 0.1035,
+      "mean_token_accuracy": 0.9549568623304368,
+      "num_tokens": 1532874.0,
+      "step": 190
+    },
+    {
+      "epoch": 1.6821052631578948,
+      "grad_norm": 0.09369785338640213,
+      "learning_rate": 8.936284237124778e-05,
+      "loss": 0.1044,
+      "mean_token_accuracy": 0.9551588267087936,
+      "num_tokens": 1611823.0,
+      "step": 200
+    },
+    {
+      "epoch": 1.6821052631578948,
+      "eval_loss": 0.10525871068239212,
+      "eval_mean_token_accuracy": 0.9543446852610662,
+      "eval_num_tokens": 1611823.0,
+      "eval_runtime": 3.4604,
+      "eval_samples_per_second": 28.899,
+      "eval_steps_per_second": 3.757,
+      "step": 200
+    },
+    {
+      "epoch": 1.7663157894736843,
+      "grad_norm": 0.09880904853343964,
+      "learning_rate": 8.020701351640182e-05,
+      "loss": 0.1045,
+      "mean_token_accuracy": 0.9547461196780205,
+      "num_tokens": 1692230.0,
+      "step": 210
+    },
+    {
+      "epoch": 1.8505263157894736,
+      "grad_norm": 0.07497906684875488,
+      "learning_rate": 7.122104846288064e-05,
+      "loss": 0.1024,
+      "mean_token_accuracy": 0.9548232913017273,
+      "num_tokens": 1774458.0,
+      "step": 220
+    },
+    {
+      "epoch": 1.9347368421052633,
+      "grad_norm": 0.09438126534223557,
+      "learning_rate": 6.248206494043313e-05,
+      "loss": 0.104,
+      "mean_token_accuracy": 0.9549880161881447,
+      "num_tokens": 1853023.0,
+      "step": 230
+    },
+    {
+      "epoch": 2.0168421052631578,
+      "grad_norm": 0.09313005208969116,
+      "learning_rate": 5.4065061078425315e-05,
+      "loss": 0.103,
+      "mean_token_accuracy": 0.9549200183305985,
+      "num_tokens": 1930647.0,
+      "step": 240
+    },
+    {
+      "epoch": 2.1010526315789475,
+      "grad_norm": 0.07283347845077515,
+      "learning_rate": 4.604227177041156e-05,
+      "loss": 0.1019,
+      "mean_token_accuracy": 0.9548763617873192,
+      "num_tokens": 2014768.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.1010526315789475,
+      "eval_loss": 0.10490619391202927,
+      "eval_mean_token_accuracy": 0.9543710763637836,
+      "eval_num_tokens": 2014768.0,
+      "eval_runtime": 3.4547,
+      "eval_samples_per_second": 28.946,
+      "eval_steps_per_second": 3.763,
+      "step": 250
+    },
+    {
+      "epoch": 2.185263157894737,
+      "grad_norm": 0.0957074984908104,
+      "learning_rate": 3.848254875285e-05,
+      "loss": 0.103,
+      "mean_token_accuracy": 0.955729816854,
+      "num_tokens": 2094236.0,
+      "step": 260
+    },
+    {
+      "epoch": 2.269473684210526,
+      "grad_norm": 0.08435027301311493,
+      "learning_rate": 3.145076971813891e-05,
+      "loss": 0.1027,
+      "mean_token_accuracy": 0.9557207286357879,
+      "num_tokens": 2173722.0,
+      "step": 270
+    },
+    {
+      "epoch": 2.353684210526316,
+      "grad_norm": 0.07077847421169281,
+      "learning_rate": 2.500728153297788e-05,
+      "loss": 0.102,
+      "mean_token_accuracy": 0.9550597742199898,
+      "num_tokens": 2256619.0,
+      "step": 280
+    },
+    {
+      "epoch": 2.437894736842105,
+      "grad_norm": 0.07486104220151901,
+      "learning_rate": 1.9207382340364634e-05,
+      "loss": 0.1024,
+      "mean_token_accuracy": 0.9555209368467331,
+      "num_tokens": 2335617.0,
+      "step": 290
+    },
+    {
+      "epoch": 2.522105263157895,
+      "grad_norm": 0.06978271156549454,
+      "learning_rate": 1.41008469898387e-05,
+      "loss": 0.1031,
+      "mean_token_accuracy": 0.9553255036473274,
+      "num_tokens": 2415889.0,
+      "step": 300
+    },
+    {
+      "epoch": 2.522105263157895,
+      "eval_loss": 0.10419522225856781,
+      "eval_mean_token_accuracy": 0.9541570269144498,
+      "eval_num_tokens": 2415889.0,
+      "eval_runtime": 3.5101,
+      "eval_samples_per_second": 28.489,
+      "eval_steps_per_second": 3.704,
+      "step": 300
+    },
+    {
+      "epoch": 2.606315789473684,
+      "grad_norm": 0.07363743335008621,
+      "learning_rate": 9.731499868738447e-06,
+      "loss": 0.1016,
+      "mean_token_accuracy": 0.9559778571128845,
+      "num_tokens": 2498011.0,
+      "step": 310
+    },
+    {
+      "epoch": 2.690526315789474,
+      "grad_norm": 0.07047491520643234,
+      "learning_rate": 6.136838800442457e-06,
+      "loss": 0.1026,
+      "mean_token_accuracy": 0.9554199263453483,
+      "num_tokens": 2576551.0,
+      "step": 320
+    },
+    {
+      "epoch": 2.774736842105263,
+      "grad_norm": 0.07501808553934097,
+      "learning_rate": 3.3477132373081254e-06,
+      "loss": 0.1014,
+      "mean_token_accuracy": 0.9564116463065148,
+      "num_tokens": 2657833.0,
+      "step": 330
+    },
+    {
+      "epoch": 2.8589473684210525,
+      "grad_norm": 0.07335389405488968,
+      "learning_rate": 1.3880595100613792e-06,
+      "loss": 0.1023,
+      "mean_token_accuracy": 0.9557045891880989,
+      "num_tokens": 2739348.0,
+      "step": 340
+    },
+    {
+      "epoch": 2.943157894736842,
+      "grad_norm": 0.06935805082321167,
+      "learning_rate": 2.746954057333606e-07,
+      "loss": 0.102,
+      "mean_token_accuracy": 0.956343337893486,
+      "num_tokens": 2817342.0,
+      "step": 350
+    },
+    {
+      "epoch": 2.943157894736842,
+      "eval_loss": 0.10404938459396362,
+      "eval_mean_token_accuracy": 0.9544462653306814,
+      "eval_num_tokens": 2817342.0,
+      "eval_runtime": 3.5152,
+      "eval_samples_per_second": 28.448,
+      "eval_steps_per_second": 3.698,
+      "step": 350
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 357,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2253434919571866e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-357/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c27b526db1ae1b28312267b5b3e8bcd79b6cbe86e77aeaa8334cf99438db39
+size 6097

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79c27b526db1ae1b28312267b5b3e8bcd79b6cbe86e77aeaa8334cf99438db39
+size 6097