Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-63/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,42 @@
+---
+language:
+- ar
+license: apache-2.0
+tags:
+- text-generation
+- fine-tuning
+- arabic
+- qwen
+datasets:
+- local
+pipeline_tag: text-generation
+---
+
+# 🧠 Thoth Text Model — InjazSmart
+
+**Thoth Text** هو نموذج لغوي عربي تم تدريبه وتحسينه باستخدام تقنية Fine-Tuning  
+بهدف تحسين الأداء في المحادثات النصية باللغة العربية والفهم السياقي العميق.
+
+---
+
+## 🧩 معلومات عامة
+- **الأساس (Base Model):** [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+- **نوع الموديل:** Text Generation / Chat
+- **المطور:** [InjazSmart](https://huggingface.co/injazsmart)
+- **اللغة:** العربية (AR)
+- **الترخيص:** Apache 2.0
+
+---
+
+## ⚙️ كيفية الاستخدام
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("injazsmart/thoth_text")
+model = AutoModelForCausalLM.from_pretrained("injazsmart/thoth_text")
+
+prompt = "اشرح بإيجاز مفهوم الذكاء الاصطناعي."
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

README.md

@@ -1,3 +1,42 @@
----
-license: apache-2.0
----
+---
+language:
+- ar
+license: apache-2.0
+tags:
+- text-generation
+- fine-tuning
+- arabic
+- qwen
+datasets:
+- local
+pipeline_tag: text-generation
+---
+
+# 🧠 Thoth Text Model — InjazSmart
+
+**Thoth Text** هو نموذج لغوي عربي تم تدريبه وتحسينه باستخدام تقنية Fine-Tuning  
+بهدف تحسين الأداء في المحادثات النصية باللغة العربية والفهم السياقي العميق.
+
+---
+
+## 🧩 معلومات عامة
+- **الأساس (Base Model):** [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+- **نوع الموديل:** Text Generation / Chat
+- **المطور:** [InjazSmart](https://huggingface.co/injazsmart)
+- **اللغة:** العربية (AR)
+- **الترخيص:** Apache 2.0
+
+---
+
+## ⚙️ كيفية الاستخدام
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("injazsmart/thoth_text")
+model = AutoModelForCausalLM.from_pretrained("injazsmart/thoth_text")
+
+prompt = "اشرح بإيجاز مفهوم الذكاء الاصطناعي."
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+outputs = model.generate(**inputs, max_new_tokens=200)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))

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": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "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 sha256:78e247e50072a6cf7a52e2e0d6258a3016ffd2e866533c145df8f41ac38718e1
+size 80792096

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-63/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-63/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": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-63/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78e247e50072a6cf7a52e2e0d6258a3016ffd2e866533c145df8f41ac38718e1
+size 80792096

checkpoint-63/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-63/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-63/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:569a26f672642370f063344eb1841ba493689f10f4bfc8faa33de06807df6b64
+size 41460101

checkpoint-63/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9bf68cc1330c69720dd641339953baacd6b2bf9e9bb41240e282995a8233c7
+size 14645

checkpoint-63/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df46d9037a5cc2c989a00c7e5584f8a9ac173aafa6941328d852b1e297f78735
+size 1465

checkpoint-63/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
+  }
+}

checkpoint-63/tokenizer.json

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

checkpoint-63/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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-63/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.5804110765457153,
+      "learning_rate": 0.00019357168190404936,
+      "loss": 2.8315,
+      "memory/device_reserved (GiB)": 21.65,
+      "memory/max_active (GiB)": 19.67,
+      "memory/max_allocated (GiB)": 19.67,
+      "step": 10,
+      "tokens_per_second_per_gpu": 1089.23
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.5418248772621155,
+      "learning_rate": 0.00016405931786981755,
+      "loss": 2.5331,
+      "memory/device_reserved (GiB)": 21.65,
+      "memory/max_active (GiB)": 17.12,
+      "memory/max_allocated (GiB)": 17.12,
+      "step": 20,
+      "tokens_per_second_per_gpu": 1399.77
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.926287829875946,
+      "learning_rate": 0.00011792807588107357,
+      "loss": 2.2908,
+      "memory/device_reserved (GiB)": 21.66,
+      "memory/max_active (GiB)": 19.67,
+      "memory/max_allocated (GiB)": 19.67,
+      "step": 30,
+      "tokens_per_second_per_gpu": 1503.62
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.741166353225708,
+      "learning_rate": 6.714576180891654e-05,
+      "loss": 2.3613,
+      "memory/device_reserved (GiB)": 21.66,
+      "memory/max_active (GiB)": 13.69,
+      "memory/max_allocated (GiB)": 13.69,
+      "step": 40,
+      "tokens_per_second_per_gpu": 1292.51
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.8406546115875244,
+      "learning_rate": 2.4886806912948035e-05,
+      "loss": 2.1182,
+      "memory/device_reserved (GiB)": 21.66,
+      "memory/max_active (GiB)": 19.67,
+      "memory/max_allocated (GiB)": 19.67,
+      "step": 50,
+      "tokens_per_second_per_gpu": 1380.03
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.7622830271720886,
+      "learning_rate": 2.1144314904642195e-06,
+      "loss": 2.1277,
+      "memory/device_reserved (GiB)": 21.66,
+      "memory/max_active (GiB)": 17.48,
+      "memory/max_allocated (GiB)": 17.48,
+      "step": 60,
+      "tokens_per_second_per_gpu": 1322.61
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2466390650454016e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bc325f0573f875c8a837ac20fbafb00d5bdae4d80f0640de382b6623c15759
+size 7313

config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

debug.log

@@ -0,0 +1,195 @@
+[2025-10-22 12:55:24,619] [DEBUG] [axolotl.utils.config.resolve_dtype:66] [PID:2418] bf16 support detected, enabling for this configuration.
+
+[2025-10-22 12:55:24,766] [DEBUG] [axolotl.utils.config.log_gpu_memory_usage:127] [PID:2418] baseline 0.000GB ()
+[2025-10-22 12:55:24,766] [INFO] [axolotl.cli.config.load_cfg:248] [PID:2418] config:
+{
+  "activation_offloading": false,
+  "adapter": "lora",
+  "axolotl_config_path": "config.yaml",
+  "base_model": "Qwen/Qwen2.5-7B-Instruct",
+  "base_model_config": "Qwen/Qwen2.5-7B-Instruct",
+  "batch_size": 16,
+  "bf16": true,
+  "capabilities": {
+    "bf16": true,
+    "compute_capability": "sm_90",
+    "fp8": false,
+    "n_gpu": 1,
+    "n_node": 1
+  },
+  "context_parallel_size": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_prefetch_factor": 256,
+  "dataset_processes": 36,
+  "datasets": [
+    {
+      "message_property_mappings": {
+        "content": "content",
+        "role": "role"
+      },
+      "path": "/workspace/fine-tuning/data/data.json",
+      "trust_remote_code": false,
+      "type": "alpaca"
+    }
+  ],
+  "ddp": false,
+  "device": "cuda:0",
+  "dion_rank_fraction": 1.0,
+  "dion_rank_multiple_of": 1,
+  "env_capabilities": {
+    "torch_version": "2.7.1"
+  },
+  "eval_batch_size": 4,
+  "eval_causal_lm_metrics": [
+    "sacrebleu",
+    "comet",
+    "ter",
+    "chrf"
+  ],
+  "eval_max_new_tokens": 128,
+  "eval_table_size": 0,
+  "experimental_skip_move_to_device": true,
+  "flash_attention": true,
+  "fp16": false,
+  "gradient_accumulation_steps": 4,
+  "gradient_checkpointing": true,
+  "gradient_checkpointing_kwargs": {
+    "use_reentrant": true
+  },
+  "include_tkps": true,
+  "learning_rate": 0.0002,
+  "lisa_layers_attribute": "model.layers",
+  "load_best_model_at_end": false,
+  "load_in_4bit": false,
+  "load_in_8bit": true,
+  "local_rank": 0,
+  "logging_steps": 10,
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "lora_r": 8,
+  "lora_target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "loraplus_lr_embedding": 1e-06,
+  "lr_scheduler": "cosine",
+  "mean_resizing_embeddings": false,
+  "micro_batch_size": 4,
+  "model_config_type": "qwen2",
+  "num_epochs": 3.0,
+  "optimizer": "adamw_bnb_8bit",
+  "output_dir": "/workspace/fine-tuning/output",
+  "pretrain_multipack_attn": true,
+  "profiler_steps_start": 0,
+  "qlora_sharded_model_loading": false,
+  "ray_num_workers": 1,
+  "resources_per_worker": {
+    "GPU": 1
+  },
+  "sample_packing_bin_size": 200,
+  "sample_packing_group_size": 100000,
+  "save_only_model": false,
+  "save_safetensors": true,
+  "save_steps": 200,
+  "save_total_limit": 2,
+  "sequence_len": 4096,
+  "shuffle_before_merging_datasets": false,
+  "shuffle_merged_datasets": true,
+  "skip_prepare_dataset": false,
+  "streaming_multipack_buffer_size": 10000,
+  "strict": false,
+  "tensor_parallel_size": 1,
+  "tiled_mlp_use_original_mlp": true,
+  "tokenizer_config": "Qwen/Qwen2.5-7B-Instruct",
+  "tokenizer_save_jinja_files": true,
+  "torch_dtype": "torch.bfloat16",
+  "train_on_inputs": false,
+  "trl": {
+    "log_completions": false,
+    "mask_truncated_completions": false,
+    "ref_model_mixup_alpha": 0.9,
+    "ref_model_sync_steps": 64,
+    "scale_rewards": true,
+    "sync_ref_model": false,
+    "use_vllm": false,
+    "vllm_server_host": "0.0.0.0",
+    "vllm_server_port": 8000
+  },
+  "use_ray": false,
+  "val_set_size": 0.0,
+  "vllm": {
+    "device": "auto",
+    "dtype": "auto",
+    "gpu_memory_utilization": 0.9,
+    "host": "0.0.0.0",
+    "port": 8000
+  },
+  "weight_decay": 0.0,
+  "world_size": 1
+}
+
+
+
+
+[2025-10-22 12:55:25,791] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:2418] EOS: 151645 / <|im_end|>
+[2025-10-22 12:55:25,792] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:2418] BOS: None / None
+[2025-10-22 12:55:25,792] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:2418] PAD: 151643 / <|endoftext|>
+[2025-10-22 12:55:25,792] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:2418] UNK: None / None
+[2025-10-22 12:55:25,792] [INFO] [axolotl.utils.data.shared.load_preprocessed_dataset:476] [PID:2418] Unable to find prepared dataset in last_run_prepared/a99a12059c50ab085817560a37dbde6c
+[2025-10-22 12:55:25,792] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:2418] Loading raw datasets...
+[2025-10-22 12:55:25,792] [WARNING] [axolotl.utils.data.sft._load_raw_datasets:322] [PID:2418] Processing datasets during training can lead to VRAM instability. Please pre-process your dataset using `axolotl preprocess path/to/config.yml`.
+
+[2025-10-22 12:55:25,923] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:2418] Loading dataset: /workspace/fine-tuning/data/data.json with base_type: alpaca and prompt_style: None
+
+[2025-10-22 12:55:30,239] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:218] [PID:2418] min_input_len: 36
+[2025-10-22 12:55:30,239] [INFO] [axolotl.utils.data.utils.handle_long_seq_in_dataset:220] [PID:2418] max_input_len: 1350
+
+
+[2025-10-22 12:55:31,719] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:404] [PID:2418] total_num_tokens: 94_264
+[2025-10-22 12:55:31,721] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:422] [PID:2418] `total_supervised_tokens: 82_964`
+[2025-10-22 12:55:31,721] [DEBUG] [axolotl.utils.trainer.calculate_total_num_steps:520] [PID:2418] total_num_steps: 63
+[2025-10-22 12:55:31,721] [INFO] [axolotl.utils.data.sft._prepare_standard_dataset:121] [PID:2418] Maximum number of steps set at 63
+[2025-10-22 12:55:31,750] [DEBUG] [axolotl.train.setup_model_and_tokenizer:65] [PID:2418] Loading tokenizer... Qwen/Qwen2.5-7B-Instruct
+[2025-10-22 12:55:32,146] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:278] [PID:2418] EOS: 151645 / <|im_end|>
+[2025-10-22 12:55:32,147] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:279] [PID:2418] BOS: None / None
+[2025-10-22 12:55:32,147] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:280] [PID:2418] PAD: 151643 / <|endoftext|>
+[2025-10-22 12:55:32,147] [DEBUG] [axolotl.loaders.tokenizer.load_tokenizer:281] [PID:2418] UNK: None / None
+[2025-10-22 12:55:32,147] [DEBUG] [axolotl.train.setup_model_and_tokenizer:74] [PID:2418] Loading model
+[2025-10-22 12:55:32,205] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_evaluation_loop:87] [PID:2418] Patched Trainer.evaluation_loop with nanmean loss calculation
+[2025-10-22 12:55:32,206] [DEBUG] [axolotl.monkeypatch.transformers.trainer_loss_calc.patch_maybe_log_save_evaluate:138] [PID:2418] Patched Trainer._maybe_log_save_evaluate with nanmean loss calculation
+
+
+
+
+
+
+
+[2025-10-22 12:56:50,899] [INFO] [axolotl.loaders.model._prepare_model_for_quantization:863] [PID:2418] converting PEFT model w/ prepare_model_for_kbit_training
+[2025-10-22 12:56:50,901] [INFO] [axolotl.loaders.model._configure_embedding_dtypes:345] [PID:2418] Converting modules to torch.bfloat16
+[2025-10-22 12:56:50,903] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:2418] Memory usage after model load 11.676GB (+11.676GB allocated, +13.172GB reserved)
+trainable params: 20,185,088 || all params: 7,635,801,600 || trainable%: 0.2643
+[2025-10-22 12:56:51,121] [DEBUG] [axolotl.loaders.model.log_gpu_memory_usage:127] [PID:2418] after adapters 8.565GB (+8.565GB allocated, +13.248GB reserved)
+[2025-10-22 12:56:57,347] [INFO] [axolotl.train.save_initial_configs:398] [PID:2418] Pre-saving adapter config to /workspace/fine-tuning/output...
+[2025-10-22 12:56:57,347] [INFO] [axolotl.train.save_initial_configs:402] [PID:2418] Pre-saving tokenizer to /workspace/fine-tuning/output...
+[2025-10-22 12:56:57,464] [INFO] [axolotl.train.save_initial_configs:407] [PID:2418] Pre-saving model config to /workspace/fine-tuning/output...
+[2025-10-22 12:56:57,466] [INFO] [axolotl.train.execute_training:196] [PID:2418] Starting trainer...
+
  0%|                                                                                                                             | 0/63 [00:00<?, ?it/s][2025-10-22 12:56:58,802] [WARNING] [py.warnings._showwarnmsg:110] [PID:2418] /root/miniconda3/envs/py3.11/lib/python3.11/site-packages/bitsandbytes/autograd/_functions.py:186: UserWarning: MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization
+  warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
+
+
  2%|█▊                                                                                                                   | 1/63 [00:04<04:23,  4.24s/it]
  3%|███▋                                                                                                                 | 2/63 [00:07<03:35,  3.53s/it]
  5%|█████▌                                                                                                               | 3/63 [00:10<03:29,  3.50s/it]
  6%|███████▍                                                                                                             | 4/63 [00:13<03:15,  3.31s/it]
  8%|█████████▎                                                                                                           | 5/63 [00:16<03:06,  3.22s/it]
 10%|███████████▏                                                                                                         | 6/63 [00:19<03:01,  3.19s/it]
 11%|█████████████                                                                                                        | 7/63 [00:22<02:50,  3.04s/it]
 13%|██████████████▊                                                                                                      | 8/63 [00:25<02:46,  3.03s/it]
 14%|████████████████▋                                                                                                    | 9/63 [00:28<02:39,  2.95s/it]
 16%|██████████████████▍                                                                                                 | 10/63 [00:32<02:49,  3.20s/it]
                                                                                                                                                         
+
 16%|██████████████████▍                                                                                                 | 10/63 [00:32<02:49,  3.20s/it]
 17%|████████████████████▎                                                                                               | 11/63 [00:35<02:52,  3.32s/it]
 19%|██████████████████████                                                                                              | 12/63 [00:38<02:41,  3.17s/it]
 21%|███████████████████████▉                                                                                            | 13/63 [00:41<02:33,  3.08s/it]
 22%|█████████████████████████▊                                                                                          | 14/63 [00:44<02:23,  2.93s/it]
 24%|███████████████████████████▌                                                                                        | 15/63 [00:47<02:21,  2.95s/it]
 25%|█████████████████████████████▍                                                                                      | 16/63 [00:50<02:20,  2.98s/it]
 27%|███████████████████████████████▎                                                                                    | 17/63 [00:52<02:13,  2.91s/it]
 29%|█████████████████████████████████▏                                                                                  | 18/63 [00:55<02:11,  2.93s/it]
 30%|██████████████████████████████████▉                                                                                 | 19/63 [00:58<02:06,  2.87s/it]
 32%|████████████████████████████████████▊                                                                               | 20/63 [01:01<02:02,  2.85s/it]
                                                                                                                                                         
+
 32%|████████████████████████████████████▊                                                                               | 20/63 [01:01<02:02,  2.85s/it]
 33%|██████████████████████████████████████▋                                                                             | 21/63 [01:04<01:58,  2.82s/it]
 35%|████████████████████████████████████████▌                                                                           | 22/63 [01:07<02:00,  2.94s/it]
 37%|██████████████████████████████████████████▎                                                                         | 23/63 [01:09<01:53,  2.83s/it]
 38%|████████████████████████████████████████████▏                                                                       | 24/63 [01:13<01:57,  3.01s/it]
 40%|██████████████████████████████████████████████                                                                      | 25/63 [01:16<01:51,  2.93s/it]
 41%|███████████████████████████████████████████████▊                                                                    | 26/63 [01:18<01:46,  2.87s/it]
 43%|█████████████████████████████████████████████████▋                                                                  | 27/63 [01:21<01:45,  2.93s/it]
 44%|███████████████████████████████████████████████████▌                                                                | 28/63 [01:25<01:51,  3.19s/it]
 46%|█████████████████████████████████████████████████████▍                                                              | 29/63 [01:28<01:46,  3.15s/it]
 48%|███████████████████████████████████████████████████████▏                                                            | 30/63 [01:31<01:38,  2.97s/it]
                                                                                                                                                         
+
 48%|███████████████████████████████████████████████████████▏                                                            | 30/63 [01:31<01:38,  2.97s/it]
 49%|█████████████████████████████████████████████████████████                                                           | 31/63 [01:33<01:30,  2.84s/it]
 51%|██████████████████████████████████████████████████████████▉                                                         | 32/63 [01:36<01:28,  2.85s/it]
 52%|████████████████████████████████████████████████████████████▊                                                       | 33/63 [01:39<01:25,  2.84s/it]
 54%|██████████████████████████████████████████████████████████████▌                                                     | 34/63 [01:42<01:23,  2.87s/it]
 56%|████████████████████████████████████████████████████████████████▍                                                   | 35/63 [01:45<01:17,  2.78s/it]
 57%|██████████████████████████████████████████████████████████████████▎                                                 | 36/63 [01:48<01:17,  2.87s/it]
 59%|████████████████████████████████████████████████████████████████████▏                                               | 37/63 [01:50<01:13,  2.84s/it]
 60%|█████████████████████████████████████████████████████████████████████▉                                              | 38/63 [01:53<01:12,  2.90s/it]
 62%|███████████████████████████████████████████████████████████████████████▊                                            | 39/63 [01:56<01:10,  2.93s/it]
 63%|█████████████████████████████████████████████████████████████████████████▋                                          | 40/63 [01:59<01:07,  2.95s/it]
                                                                                                                                                         
+
 63%|█████████████████████████████████████████████████████████████████████████▋                                          | 40/63 [01:59<01:07,  2.95s/it]
 65%|███████████████████████████████████████████████████████████████████████████▍                                        | 41/63 [02:02<01:05,  2.97s/it]
 67%|█████████████████████████████████████████████████████████████████████████████▎                                      | 42/63 [02:05<01:01,  2.91s/it]
 68%|███████████████████████████████████████████████████████████████████████████████▏                                    | 43/63 [02:08<01:00,  3.02s/it]
 70%|█████████████████████████████████████████████████████████████████████████████████                                   | 44/63 [02:12<01:00,  3.20s/it]
 71%|██████████████████████████████████████████████████████████████████████████████████▊                                 | 45/63 [02:15<00:56,  3.11s/it]
 73%|████████████████████████████████████████████████████████████████████████████████████▋                               | 46/63 [02:18<00:52,  3.11s/it]
 75%|██████████████████████████████████████████████████████████████████████████████████████▌                             | 47/63 [02:21<00:49,  3.08s/it]
 76%|████████████████████████████████████████████████████████████████████████████████████████▍                           | 48/63 [02:25<00:48,  3.23s/it]
 78%|██████████████████████████████████████████████████████████████████████████████████████████▏                         | 49/63 [02:28<00:43,  3.10s/it]
 79%|████████████████████████████████████████████████████████████████████████████████████████████                        | 50/63 [02:31<00:39,  3.07s/it]
                                                                                                                                                         
+
 79%|████████████████████████████████████████████████████████████████████████████████████████████                        | 50/63 [02:31<00:39,  3.07s/it]
 81%|█████████████████████████████████████████████████████████████████████████████████████████████▉                      | 51/63 [02:33<00:35,  2.97s/it]
 83%|███████████████████████████████████████████████████████████████████████████████████████████████▋                    | 52/63 [02:36<00:32,  2.93s/it]
 84%|█████████████████████████████████████████████████████████████████████████████████████████████████▌                  | 53/63 [02:39<00:29,  2.92s/it]
 86%|███████████████████████████████████████████████████████████████████████████████████████████████████▍                | 54/63 [02:42<00:26,  2.92s/it]
 87%|█████████████████████████████████████████████████████████████████████████████████████████████████████▎              | 55/63 [02:45<00:23,  2.91s/it]
 89%|███████████████████████████████████████████████████████████████████████████████████████████████████████             | 56/63 [02:48<00:20,  2.91s/it]
 90%|████████████████████████████████████████████████████████████████████████████████████████████████████████▉           | 57/63 [02:51<00:18,  3.04s/it]
 92%|██████████████████████████████████████████████████████████████████████████████████████████████████████████▊         | 58/63 [02:54<00:14,  2.99s/it]
 94%|████████████████████████████████████████████████████████████████████████████████████████████████████████████▋       | 59/63 [02:57<00:11,  2.95s/it]
 95%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████▍     | 60/63 [03:00<00:08,  2.95s/it]
                                                                                                                                                         
+
 95%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████▍     | 60/63 [03:00<00:08,  2.95s/it]
 97%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎   | 61/63 [03:03<00:05,  2.92s/it]
 98%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 62/63 [03:05<00:02,  2.91s/it]
+
                                                                                                                                                         
+
+[2025-10-22 13:00:08,876] [INFO] [axolotl.train.save_trained_model:218] [PID:2418] Training completed! Saving trained model to /workspace/fine-tuning/output.
+[2025-10-22 13:00:09,025] [INFO] [axolotl.train.save_trained_model:336] [PID:2418] Model successfully saved to /workspace/fine-tuning/output

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
+  }
+}

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": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}