iscchang/Qwen2.5-Coder-Text2Sql-ft

.gitattributes

@@ -33,3 +33,9 @@ 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
+workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+workspace/fine_tunning/text2sql/output_train2/checkpoint-2250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+workspace/fine_tunning/text2sql/output_train2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+workspace/fine_tunning/text2sql/output_train2/tokenizer.json filter=lfs diff=lfs merge=lfs -text

workspace/fine_tunning/text2sql/output_train2/README.md

@@ -0,0 +1,59 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+model_name: output_train2
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for output_train2
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-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 0.15.2
+- TRL: 0.19.0
+- Transformers: 4.53.0
+- Pytorch: 2.6.0+cu126
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## 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}}
+}
+```

workspace/fine_tunning/text2sql/output_train2/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "v_projup_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

workspace/fine_tunning/text2sql/output_train2/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6835f0cb8e90c9ec4e5da4246f61ef38f8d6956ab17bce0c708ca89db90551c6
+size 455119848

workspace/fine_tunning/text2sql/output_train2/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
+}

workspace/fine_tunning/text2sql/output_train2/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 %}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "v_projup_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37b63a5e28ce0db56c2b98c2b165ad867a1fd47bd7240c23c289abe0d4b8582c
+size 455119848

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/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
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/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 %}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116804cc3cccddf34a127ce1758e0b241b78f44db18edba2c0e2c3c3feeb57cd
+size 910403834

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359aeabb4a541fe389e7688702069992cdde94563b1e8f786cd1758edd8e161c
+size 14244

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c34ba9e6f50c2313df84e91c7dfed2be6b77dec7394adba34d3bd12d40d5ba2d
+size 1064

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/tokenizer.json

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

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.2222222222222223,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.20243267714977264,
+      "learning_rate": 5e-05,
+      "loss": 0.1508,
+      "mean_token_accuracy": 0.9614167541265488,
+      "num_tokens": 172590.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.22473949193954468,
+      "learning_rate": 5e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.974150316119194,
+      "num_tokens": 346277.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.1306583136320114,
+      "learning_rate": 5e-05,
+      "loss": 0.059,
+      "mean_token_accuracy": 0.9791698586940766,
+      "num_tokens": 521548.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.2091003954410553,
+      "learning_rate": 5e-05,
+      "loss": 0.0511,
+      "mean_token_accuracy": 0.9820115834474563,
+      "num_tokens": 694583.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.18803296983242035,
+      "learning_rate": 5e-05,
+      "loss": 0.0443,
+      "mean_token_accuracy": 0.9839017766714097,
+      "num_tokens": 868203.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19305875897407532,
+      "learning_rate": 5e-05,
+      "loss": 0.0484,
+      "mean_token_accuracy": 0.9826253122091293,
+      "num_tokens": 1044270.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.16429616510868073,
+      "learning_rate": 5e-05,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9832556092739105,
+      "num_tokens": 1221728.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.17009682953357697,
+      "learning_rate": 5e-05,
+      "loss": 0.0419,
+      "mean_token_accuracy": 0.9852031743526459,
+      "num_tokens": 1395873.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14838816225528717,
+      "learning_rate": 5e-05,
+      "loss": 0.0458,
+      "mean_token_accuracy": 0.9842678928375244,
+      "num_tokens": 1570780.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.20167161524295807,
+      "learning_rate": 5e-05,
+      "loss": 0.0335,
+      "mean_token_accuracy": 0.9871636009216309,
+      "num_tokens": 1746181.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.22028109431266785,
+      "learning_rate": 5e-05,
+      "loss": 0.0338,
+      "mean_token_accuracy": 0.9862233906984329,
+      "num_tokens": 1921414.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12278841435909271,
+      "learning_rate": 5e-05,
+      "loss": 0.0299,
+      "mean_token_accuracy": 0.9886959612369537,
+      "num_tokens": 2095976.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.09097229689359665,
+      "learning_rate": 5e-05,
+      "loss": 0.0344,
+      "mean_token_accuracy": 0.9869739925861358,
+      "num_tokens": 2269976.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.149724543094635,
+      "learning_rate": 5e-05,
+      "loss": 0.0312,
+      "mean_token_accuracy": 0.9881853342056275,
+      "num_tokens": 2444238.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.1601683348417282,
+      "learning_rate": 5e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9859996843338013,
+      "num_tokens": 2618992.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.14399662613868713,
+      "learning_rate": 5e-05,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9900204366445542,
+      "num_tokens": 2793057.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.1325361728668213,
+      "learning_rate": 5e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.9859159809350967,
+      "num_tokens": 2966769.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.12275587767362595,
+      "learning_rate": 5e-05,
+      "loss": 0.0359,
+      "mean_token_accuracy": 0.9860490292310715,
+      "num_tokens": 3141560.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.14534829556941986,
+      "learning_rate": 5e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9910678189992904,
+      "num_tokens": 3315113.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.1087908148765564,
+      "learning_rate": 5e-05,
+      "loss": 0.0281,
+      "mean_token_accuracy": 0.9884923130273819,
+      "num_tokens": 3488791.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5866994635322163e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c34f0e72d09e9403ea641d661ee4a3837b148358641ce83b44fb1187ce178ca
+size 5688

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "v_projup_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c7ba39e0ac935b0bd8ab663834d497f86b242740c1ad43e355d4aa488d93dc9
+size 455119848

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/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
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/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 %}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11888d8f4029e5c11ef8daa7b71e250b9ea8c998c29045c1c3495192d96d9741
+size 910403834

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4542f3b0241e13a0d9de6b883b01ad96085f320e35e522f9dfad79b33ba6afcf
+size 14244

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084c8aecb9d3ac85c94f614df2060324a90d5a59efa400ab27a1733b0fc8abfb
+size 1064

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/tokenizer.json

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

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.3333333333333335,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.20243267714977264,
+      "learning_rate": 5e-05,
+      "loss": 0.1508,
+      "mean_token_accuracy": 0.9614167541265488,
+      "num_tokens": 172590.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.22473949193954468,
+      "learning_rate": 5e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.974150316119194,
+      "num_tokens": 346277.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.1306583136320114,
+      "learning_rate": 5e-05,
+      "loss": 0.059,
+      "mean_token_accuracy": 0.9791698586940766,
+      "num_tokens": 521548.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.2091003954410553,
+      "learning_rate": 5e-05,
+      "loss": 0.0511,
+      "mean_token_accuracy": 0.9820115834474563,
+      "num_tokens": 694583.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.18803296983242035,
+      "learning_rate": 5e-05,
+      "loss": 0.0443,
+      "mean_token_accuracy": 0.9839017766714097,
+      "num_tokens": 868203.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19305875897407532,
+      "learning_rate": 5e-05,
+      "loss": 0.0484,
+      "mean_token_accuracy": 0.9826253122091293,
+      "num_tokens": 1044270.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.16429616510868073,
+      "learning_rate": 5e-05,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9832556092739105,
+      "num_tokens": 1221728.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.17009682953357697,
+      "learning_rate": 5e-05,
+      "loss": 0.0419,
+      "mean_token_accuracy": 0.9852031743526459,
+      "num_tokens": 1395873.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14838816225528717,
+      "learning_rate": 5e-05,
+      "loss": 0.0458,
+      "mean_token_accuracy": 0.9842678928375244,
+      "num_tokens": 1570780.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.20167161524295807,
+      "learning_rate": 5e-05,
+      "loss": 0.0335,
+      "mean_token_accuracy": 0.9871636009216309,
+      "num_tokens": 1746181.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.22028109431266785,
+      "learning_rate": 5e-05,
+      "loss": 0.0338,
+      "mean_token_accuracy": 0.9862233906984329,
+      "num_tokens": 1921414.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12278841435909271,
+      "learning_rate": 5e-05,
+      "loss": 0.0299,
+      "mean_token_accuracy": 0.9886959612369537,
+      "num_tokens": 2095976.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.09097229689359665,
+      "learning_rate": 5e-05,
+      "loss": 0.0344,
+      "mean_token_accuracy": 0.9869739925861358,
+      "num_tokens": 2269976.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.149724543094635,
+      "learning_rate": 5e-05,
+      "loss": 0.0312,
+      "mean_token_accuracy": 0.9881853342056275,
+      "num_tokens": 2444238.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.1601683348417282,
+      "learning_rate": 5e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9859996843338013,
+      "num_tokens": 2618992.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.14399662613868713,
+      "learning_rate": 5e-05,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9900204366445542,
+      "num_tokens": 2793057.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.1325361728668213,
+      "learning_rate": 5e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.9859159809350967,
+      "num_tokens": 2966769.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.12275587767362595,
+      "learning_rate": 5e-05,
+      "loss": 0.0359,
+      "mean_token_accuracy": 0.9860490292310715,
+      "num_tokens": 3141560.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.14534829556941986,
+      "learning_rate": 5e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9910678189992904,
+      "num_tokens": 3315113.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.1087908148765564,
+      "learning_rate": 5e-05,
+      "loss": 0.0281,
+      "mean_token_accuracy": 0.9884923130273819,
+      "num_tokens": 3488791.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.16228517889976501,
+      "learning_rate": 5e-05,
+      "loss": 0.0234,
+      "mean_token_accuracy": 0.9911258590221405,
+      "num_tokens": 3663372.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.05340925231575966,
+      "learning_rate": 5e-05,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9899671649932862,
+      "num_tokens": 3837397.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.12148639559745789,
+      "learning_rate": 5e-05,
+      "loss": 0.0296,
+      "mean_token_accuracy": 0.9886352431774139,
+      "num_tokens": 4012362.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.09275887161493301,
+      "learning_rate": 5e-05,
+      "loss": 0.0269,
+      "mean_token_accuracy": 0.989583585858345,
+      "num_tokens": 4188410.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.17173512279987335,
+      "learning_rate": 5e-05,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9893661296367645,
+      "num_tokens": 4364549.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.18386530876159668,
+      "learning_rate": 5e-05,
+      "loss": 0.03,
+      "mean_token_accuracy": 0.9877435737848281,
+      "num_tokens": 4538708.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0737985298037529,
+      "learning_rate": 5e-05,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9906050026416778,
+      "num_tokens": 4712340.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 0.10669398307800293,
+      "learning_rate": 5e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9914622634649277,
+      "num_tokens": 4887386.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.09974446147680283,
+      "learning_rate": 5e-05,
+      "loss": 0.0212,
+      "mean_token_accuracy": 0.9920986944437027,
+      "num_tokens": 5059979.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.18398422002792358,
+      "learning_rate": 5e-05,
+      "loss": 0.0229,
+      "mean_token_accuracy": 0.9908855521678924,
+      "num_tokens": 5233989.0,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.380832868519383e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c34f0e72d09e9403ea641d661ee4a3837b148358641ce83b44fb1187ce178ca
+size 5688

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+library_name: peft
+---
+
+# 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 0.15.2

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "v_projup_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c36a604ca0ca61be7a5442b1177ba0a70c8d9ab70e3d37c0dbedc6f5efcffb6
+size 455119848

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/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
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/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 %}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d00dcbfbd482e0ca5ad1b07e54b65d03d868642522497a4da7c80d2ee73ffdbe
+size 910403834

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa44244e0925db8fbb09067e4fff995b293c441bb88dcdcd88177ca4a144d46
+size 14244

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:115fc5d3c71fc8b112d5c1701359950aa4e48ea559451a73de1d1d8ca1116d89
+size 1064

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/tokenizer.json

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

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/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": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/trainer_state.json

@@ -0,0 +1,394 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.444444444444445,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.20243267714977264,
+      "learning_rate": 5e-05,
+      "loss": 0.1508,
+      "mean_token_accuracy": 0.9614167541265488,
+      "num_tokens": 172590.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 0.22473949193954468,
+      "learning_rate": 5e-05,
+      "loss": 0.0762,
+      "mean_token_accuracy": 0.974150316119194,
+      "num_tokens": 346277.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.1306583136320114,
+      "learning_rate": 5e-05,
+      "loss": 0.059,
+      "mean_token_accuracy": 0.9791698586940766,
+      "num_tokens": 521548.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.2091003954410553,
+      "learning_rate": 5e-05,
+      "loss": 0.0511,
+      "mean_token_accuracy": 0.9820115834474563,
+      "num_tokens": 694583.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.18803296983242035,
+      "learning_rate": 5e-05,
+      "loss": 0.0443,
+      "mean_token_accuracy": 0.9839017766714097,
+      "num_tokens": 868203.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.19305875897407532,
+      "learning_rate": 5e-05,
+      "loss": 0.0484,
+      "mean_token_accuracy": 0.9826253122091293,
+      "num_tokens": 1044270.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.7777777777777778,
+      "grad_norm": 0.16429616510868073,
+      "learning_rate": 5e-05,
+      "loss": 0.0452,
+      "mean_token_accuracy": 0.9832556092739105,
+      "num_tokens": 1221728.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.17009682953357697,
+      "learning_rate": 5e-05,
+      "loss": 0.0419,
+      "mean_token_accuracy": 0.9852031743526459,
+      "num_tokens": 1395873.0,
+      "step": 400
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14838816225528717,
+      "learning_rate": 5e-05,
+      "loss": 0.0458,
+      "mean_token_accuracy": 0.9842678928375244,
+      "num_tokens": 1570780.0,
+      "step": 450
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 0.20167161524295807,
+      "learning_rate": 5e-05,
+      "loss": 0.0335,
+      "mean_token_accuracy": 0.9871636009216309,
+      "num_tokens": 1746181.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.2222222222222223,
+      "grad_norm": 0.22028109431266785,
+      "learning_rate": 5e-05,
+      "loss": 0.0338,
+      "mean_token_accuracy": 0.9862233906984329,
+      "num_tokens": 1921414.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.12278841435909271,
+      "learning_rate": 5e-05,
+      "loss": 0.0299,
+      "mean_token_accuracy": 0.9886959612369537,
+      "num_tokens": 2095976.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.4444444444444444,
+      "grad_norm": 0.09097229689359665,
+      "learning_rate": 5e-05,
+      "loss": 0.0344,
+      "mean_token_accuracy": 0.9869739925861358,
+      "num_tokens": 2269976.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.5555555555555556,
+      "grad_norm": 0.149724543094635,
+      "learning_rate": 5e-05,
+      "loss": 0.0312,
+      "mean_token_accuracy": 0.9881853342056275,
+      "num_tokens": 2444238.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.1601683348417282,
+      "learning_rate": 5e-05,
+      "loss": 0.0375,
+      "mean_token_accuracy": 0.9859996843338013,
+      "num_tokens": 2618992.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 0.14399662613868713,
+      "learning_rate": 5e-05,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9900204366445542,
+      "num_tokens": 2793057.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.8888888888888888,
+      "grad_norm": 0.1325361728668213,
+      "learning_rate": 5e-05,
+      "loss": 0.037,
+      "mean_token_accuracy": 0.9859159809350967,
+      "num_tokens": 2966769.0,
+      "step": 850
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.12275587767362595,
+      "learning_rate": 5e-05,
+      "loss": 0.0359,
+      "mean_token_accuracy": 0.9860490292310715,
+      "num_tokens": 3141560.0,
+      "step": 900
+    },
+    {
+      "epoch": 2.111111111111111,
+      "grad_norm": 0.14534829556941986,
+      "learning_rate": 5e-05,
+      "loss": 0.0238,
+      "mean_token_accuracy": 0.9910678189992904,
+      "num_tokens": 3315113.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.1087908148765564,
+      "learning_rate": 5e-05,
+      "loss": 0.0281,
+      "mean_token_accuracy": 0.9884923130273819,
+      "num_tokens": 3488791.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.16228517889976501,
+      "learning_rate": 5e-05,
+      "loss": 0.0234,
+      "mean_token_accuracy": 0.9911258590221405,
+      "num_tokens": 3663372.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.4444444444444446,
+      "grad_norm": 0.05340925231575966,
+      "learning_rate": 5e-05,
+      "loss": 0.0254,
+      "mean_token_accuracy": 0.9899671649932862,
+      "num_tokens": 3837397.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.5555555555555554,
+      "grad_norm": 0.12148639559745789,
+      "learning_rate": 5e-05,
+      "loss": 0.0296,
+      "mean_token_accuracy": 0.9886352431774139,
+      "num_tokens": 4012362.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.09275887161493301,
+      "learning_rate": 5e-05,
+      "loss": 0.0269,
+      "mean_token_accuracy": 0.989583585858345,
+      "num_tokens": 4188410.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 0.17173512279987335,
+      "learning_rate": 5e-05,
+      "loss": 0.0275,
+      "mean_token_accuracy": 0.9893661296367645,
+      "num_tokens": 4364549.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.888888888888889,
+      "grad_norm": 0.18386530876159668,
+      "learning_rate": 5e-05,
+      "loss": 0.03,
+      "mean_token_accuracy": 0.9877435737848281,
+      "num_tokens": 4538708.0,
+      "step": 1300
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.0737985298037529,
+      "learning_rate": 5e-05,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9906050026416778,
+      "num_tokens": 4712340.0,
+      "step": 1350
+    },
+    {
+      "epoch": 3.111111111111111,
+      "grad_norm": 0.10669398307800293,
+      "learning_rate": 5e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9914622634649277,
+      "num_tokens": 4887386.0,
+      "step": 1400
+    },
+    {
+      "epoch": 3.2222222222222223,
+      "grad_norm": 0.09974446147680283,
+      "learning_rate": 5e-05,
+      "loss": 0.0212,
+      "mean_token_accuracy": 0.9920986944437027,
+      "num_tokens": 5059979.0,
+      "step": 1450
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.18398422002792358,
+      "learning_rate": 5e-05,
+      "loss": 0.0229,
+      "mean_token_accuracy": 0.9908855521678924,
+      "num_tokens": 5233989.0,
+      "step": 1500
+    },
+    {
+      "epoch": 3.4444444444444446,
+      "grad_norm": 0.10202126950025558,
+      "learning_rate": 5e-05,
+      "loss": 0.0236,
+      "mean_token_accuracy": 0.9902925211191177,
+      "num_tokens": 5410888.0,
+      "step": 1550
+    },
+    {
+      "epoch": 3.5555555555555554,
+      "grad_norm": 0.1483769565820694,
+      "learning_rate": 5e-05,
+      "loss": 0.0244,
+      "mean_token_accuracy": 0.9899595558643342,
+      "num_tokens": 5584175.0,
+      "step": 1600
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.07508880645036697,
+      "learning_rate": 5e-05,
+      "loss": 0.0226,
+      "mean_token_accuracy": 0.9916278702020646,
+      "num_tokens": 5759747.0,
+      "step": 1650
+    },
+    {
+      "epoch": 3.7777777777777777,
+      "grad_norm": 0.08631623536348343,
+      "learning_rate": 5e-05,
+      "loss": 0.0252,
+      "mean_token_accuracy": 0.9896138072013855,
+      "num_tokens": 5933352.0,
+      "step": 1700
+    },
+    {
+      "epoch": 3.888888888888889,
+      "grad_norm": 0.12719225883483887,
+      "learning_rate": 5e-05,
+      "loss": 0.0213,
+      "mean_token_accuracy": 0.9918474739789963,
+      "num_tokens": 6108120.0,
+      "step": 1750
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.07570526748895645,
+      "learning_rate": 5e-05,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.990051948428154,
+      "num_tokens": 6283120.0,
+      "step": 1800
+    },
+    {
+      "epoch": 4.111111111111111,
+      "grad_norm": 0.7129213213920593,
+      "learning_rate": 5e-05,
+      "loss": 0.0181,
+      "mean_token_accuracy": 0.9931919860839844,
+      "num_tokens": 6456943.0,
+      "step": 1850
+    },
+    {
+      "epoch": 4.222222222222222,
+      "grad_norm": 0.132768452167511,
+      "learning_rate": 5e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9916618072986603,
+      "num_tokens": 6632907.0,
+      "step": 1900
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.1010010689496994,
+      "learning_rate": 5e-05,
+      "loss": 0.0212,
+      "mean_token_accuracy": 0.9916968619823456,
+      "num_tokens": 6805656.0,
+      "step": 1950
+    },
+    {
+      "epoch": 4.444444444444445,
+      "grad_norm": 0.22385317087173462,
+      "learning_rate": 5e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.9914450365304946,
+      "num_tokens": 6978299.0,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.174835230239662e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

workspace/fine_tunning/text2sql/output_train2/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c34f0e72d09e9403ea641d661ee4a3837b148358641ce83b44fb1187ce178ca
+size 5688