Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,7 @@ 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-282/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-287/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-574/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,63 @@
+---
+base_model: unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+library_name: peft
+model_name: qwen-detection-lora
+tags:
+- base_model:adapter:unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for qwen-detection-lora
+
+This model is a fine-tuned version of [unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.24.0
+- Transformers: 5.5.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.3.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b03eeb85da9c20e89ff75774b62d8951ce9dc1fc7a7d0192256ea9b46367ff
+size 73911112

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-282/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-282/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-282/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b03eeb85da9c20e89ff75774b62d8951ce9dc1fc7a7d0192256ea9b46367ff
+size 73911112

checkpoint-282/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-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5f6c971d3464fa17faca602f5b55d0a0f0eb7365790ffa472bc15cfafd6a4a
+size 37974661

checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-282/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0e71e5c9aaa220d58178094eab4988ab135b6ba1066da12d997b682a2b141f
+size 1383

checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f662027000969bd5c53794b1cc5f79566a2685a3b174c35097cd8419c58d83d
+size 1465

checkpoint-282/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-282/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-282/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03546099290780142,
+      "grad_norm": 1.3688955307006836,
+      "learning_rate": 9e-05,
+      "loss": 3.273609924316406,
+      "step": 10
+    },
+    {
+      "epoch": 0.07092198581560284,
+      "grad_norm": 1.6823779344558716,
+      "learning_rate": 0.00019,
+      "loss": 2.013600540161133,
+      "step": 20
+    },
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 1.3549606800079346,
+      "learning_rate": 0.0001994182576820673,
+      "loss": 0.9827978134155273,
+      "step": 30
+    },
+    {
+      "epoch": 0.14184397163120568,
+      "grad_norm": 0.704963207244873,
+      "learning_rate": 0.00019741598475167175,
+      "loss": 0.6513552665710449,
+      "step": 40
+    },
+    {
+      "epoch": 0.1773049645390071,
+      "grad_norm": 0.5734719038009644,
+      "learning_rate": 0.0001940147464327637,
+      "loss": 0.5401387691497803,
+      "step": 50
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 0.7053222060203552,
+      "learning_rate": 0.00018926338701612738,
+      "loss": 0.5485860347747803,
+      "step": 60
+    },
+    {
+      "epoch": 0.24822695035460993,
+      "grad_norm": 0.5607346892356873,
+      "learning_rate": 0.00018323013952726875,
+      "loss": 0.5408585071563721,
+      "step": 70
+    },
+    {
+      "epoch": 0.28368794326241137,
+      "grad_norm": 0.6696723699569702,
+      "learning_rate": 0.00017600164584984546,
+      "loss": 0.5451176166534424,
+      "step": 80
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 0.6198937892913818,
+      "learning_rate": 0.00016768171248431602,
+      "loss": 0.4622413158416748,
+      "step": 90
+    },
+    {
+      "epoch": 0.3546099290780142,
+      "grad_norm": 0.49034929275512695,
+      "learning_rate": 0.00015838981981003273,
+      "loss": 0.5463218688964844,
+      "step": 100
+    },
+    {
+      "epoch": 0.3900709219858156,
+      "grad_norm": 0.46550455689430237,
+      "learning_rate": 0.00014825940625887342,
+      "loss": 0.45171518325805665,
+      "step": 110
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 0.3953458368778229,
+      "learning_rate": 0.0001374359520409444,
+      "loss": 0.43686976432800295,
+      "step": 120
+    },
+    {
+      "epoch": 0.46099290780141844,
+      "grad_norm": 0.4815589487552643,
+      "learning_rate": 0.00012607488994146704,
+      "loss": 0.518321418762207,
+      "step": 130
+    },
+    {
+      "epoch": 0.49645390070921985,
+      "grad_norm": 0.37568503618240356,
+      "learning_rate": 0.00011433937319134511,
+      "loss": 0.34571166038513185,
+      "step": 140
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 0.5359418392181396,
+      "learning_rate": 0.00010239793246643819,
+      "loss": 0.48325700759887696,
+      "step": 150
+    },
+    {
+      "epoch": 0.5673758865248227,
+      "grad_norm": 0.5425746440887451,
+      "learning_rate": 9.042205566275951e-05,
+      "loss": 0.429827356338501,
+      "step": 160
+    },
+    {
+      "epoch": 0.6028368794326241,
+      "grad_norm": 0.5164040923118591,
+      "learning_rate": 7.858372520381119e-05,
+      "loss": 0.4601579189300537,
+      "step": 170
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 0.5248101949691772,
+      "learning_rate": 6.705294824614004e-05,
+      "loss": 0.3804056644439697,
+      "step": 180
+    },
+    {
+      "epoch": 0.6737588652482269,
+      "grad_norm": 0.34143301844596863,
+      "learning_rate": 5.5995315251183734e-05,
+      "loss": 0.3424631118774414,
+      "step": 190
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 0.5679530501365662,
+      "learning_rate": 4.556962198411631e-05,
+      "loss": 0.46054668426513673,
+      "step": 200
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 0.46360042691230774,
+      "learning_rate": 3.592558908954295e-05,
+      "loss": 0.41877241134643556,
+      "step": 210
+    },
+    {
+      "epoch": 0.7801418439716312,
+      "grad_norm": 0.4703761041164398,
+      "learning_rate": 2.720171199261987e-05,
+      "loss": 0.4663556575775146,
+      "step": 220
+    },
+    {
+      "epoch": 0.8156028368794326,
+      "grad_norm": 0.530480146408081,
+      "learning_rate": 1.9523272002603742e-05,
+      "loss": 0.4497820377349854,
+      "step": 230
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.48615142703056335,
+      "learning_rate": 1.3000537180852212e-05,
+      "loss": 0.3560842275619507,
+      "step": 240
+    },
+    {
+      "epoch": 0.8865248226950354,
+      "grad_norm": 0.4983954131603241,
+      "learning_rate": 7.727178810136093e-06,
+      "loss": 0.45021347999572753,
+      "step": 250
+    },
+    {
+      "epoch": 0.9219858156028369,
+      "grad_norm": 0.5884110927581787,
+      "learning_rate": 3.778926205933342e-06,
+      "loss": 0.4234372615814209,
+      "step": 260
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 0.4866378903388977,
+      "learning_rate": 1.212479187605897e-06,
+      "loss": 0.4674375534057617,
+      "step": 270
+    },
+    {
+      "epoch": 0.9929078014184397,
+      "grad_norm": 0.4536786377429962,
+      "learning_rate": 6.469382717563255e-08,
+      "loss": 0.4669623374938965,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 282,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3881477709846528.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:175938bfc2811d85062402772ce337c2653b54681d0312e70c04d9eff31521a7
+size 5713

checkpoint-287/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-287/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-287/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef39c757952d8d7734cd16f617138a7c45fde862210d01429550fe3cdbd3e405
+size 73911112

checkpoint-287/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-287/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b8de4bb67e3a8279709406d6309929e860261c4251ca75db70a13a7aff0914d
+size 37974661

checkpoint-287/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-287/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444ee8233c1f342669af784817d5e759bca1bf2d4e05223e6a245863314e2041
+size 1383

checkpoint-287/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee61ed6361a4b5accec4c7800b9e763b75b86a90fddb81a1785581500015a58b
+size 1465

checkpoint-287/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-287/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-287/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 287,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034934497816593885,
+      "grad_norm": 1.8211296796798706,
+      "learning_rate": 9e-05,
+      "loss": 3.1205413818359373,
+      "step": 10
+    },
+    {
+      "epoch": 0.06986899563318777,
+      "grad_norm": 2.2983880043029785,
+      "learning_rate": 0.00019,
+      "loss": 1.7317464828491211,
+      "step": 20
+    },
+    {
+      "epoch": 0.10480349344978165,
+      "grad_norm": 0.7729952335357666,
+      "learning_rate": 0.00019986979101058972,
+      "loss": 0.8218430519104004,
+      "step": 30
+    },
+    {
+      "epoch": 0.13973799126637554,
+      "grad_norm": 0.7794175744056702,
+      "learning_rate": 0.00019942012118204737,
+      "loss": 0.6791059017181397,
+      "step": 40
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "grad_norm": 0.6147348880767822,
+      "learning_rate": 0.0001986508282827419,
+      "loss": 0.5647100448608399,
+      "step": 50
+    },
+    {
+      "epoch": 0.2096069868995633,
+      "grad_norm": 0.5721135139465332,
+      "learning_rate": 0.0001975643854917025,
+      "loss": 0.4464299201965332,
+      "step": 60
+    },
+    {
+      "epoch": 0.2445414847161572,
+      "grad_norm": 0.4910798668861389,
+      "learning_rate": 0.00019616428558460634,
+      "loss": 0.5486050605773926,
+      "step": 70
+    },
+    {
+      "epoch": 0.2794759825327511,
+      "grad_norm": 0.4786812365055084,
+      "learning_rate": 0.00019445502970494787,
+      "loss": 0.6309103965759277,
+      "step": 80
+    },
+    {
+      "epoch": 0.314410480349345,
+      "grad_norm": 0.3899824321269989,
+      "learning_rate": 0.00019244211289343397,
+      "loss": 0.47461185455322263,
+      "step": 90
+    },
+    {
+      "epoch": 0.34934497816593885,
+      "grad_norm": 0.21079467236995697,
+      "learning_rate": 0.00019013200642212545,
+      "loss": 0.41464600563049314,
+      "step": 100
+    },
+    {
+      "epoch": 0.38427947598253276,
+      "grad_norm": 0.42337626218795776,
+      "learning_rate": 0.00018753213699011876,
+      "loss": 0.4927196979522705,
+      "step": 110
+    },
+    {
+      "epoch": 0.4192139737991266,
+      "grad_norm": 0.4860546588897705,
+      "learning_rate": 0.00018465086284765093,
+      "loss": 0.4953155040740967,
+      "step": 120
+    },
+    {
+      "epoch": 0.45414847161572053,
+      "grad_norm": 0.5280138850212097,
+      "learning_rate": 0.0001814974469253861,
+      "loss": 0.3739574432373047,
+      "step": 130
+    },
+    {
+      "epoch": 0.4890829694323144,
+      "grad_norm": 0.3762610852718353,
+      "learning_rate": 0.000178082027055269,
+      "loss": 0.5111323833465576,
+      "step": 140
+    },
+    {
+      "epoch": 0.5240174672489083,
+      "grad_norm": 0.5376149415969849,
+      "learning_rate": 0.00017441558337868198,
+      "loss": 0.5593331813812256,
+      "step": 150
+    },
+    {
+      "epoch": 0.5589519650655022,
+      "grad_norm": 0.472368448972702,
+      "learning_rate": 0.00017050990304668423,
+      "loss": 0.5056246757507324,
+      "step": 160
+    },
+    {
+      "epoch": 0.5938864628820961,
+      "grad_norm": 0.44528254866600037,
+      "learning_rate": 0.00016637754232581698,
+      "loss": 0.4254063606262207,
+      "step": 170
+    },
+    {
+      "epoch": 0.62882096069869,
+      "grad_norm": 0.38811150193214417,
+      "learning_rate": 0.0001620317862313006,
+      "loss": 0.5141812324523926,
+      "step": 180
+    },
+    {
+      "epoch": 0.6637554585152838,
+      "grad_norm": 0.5775936841964722,
+      "learning_rate": 0.00015748660581739655,
+      "loss": 0.49105257987976075,
+      "step": 190
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 0.47975367307662964,
+      "learning_rate": 0.0001527566132622413,
+      "loss": 0.5170726299285888,
+      "step": 200
+    },
+    {
+      "epoch": 0.7336244541484717,
+      "grad_norm": 0.3569624125957489,
+      "learning_rate": 0.0001478570148915483,
+      "loss": 0.42121267318725586,
+      "step": 210
+    },
+    {
+      "epoch": 0.7685589519650655,
+      "grad_norm": 0.5059508085250854,
+      "learning_rate": 0.0001428035622922009,
+      "loss": 0.41593084335327146,
+      "step": 220
+    },
+    {
+      "epoch": 0.8034934497816594,
+      "grad_norm": 0.45586642622947693,
+      "learning_rate": 0.0001376125016728996,
+      "loss": 0.38859803676605226,
+      "step": 230
+    },
+    {
+      "epoch": 0.8384279475982532,
+      "grad_norm": 0.41792041063308716,
+      "learning_rate": 0.00013230052163466335,
+      "loss": 0.4688732147216797,
+      "step": 240
+    },
+    {
+      "epoch": 0.8733624454148472,
+      "grad_norm": 0.46951380372047424,
+      "learning_rate": 0.0001268846995190953,
+      "loss": 0.4584070682525635,
+      "step": 250
+    },
+    {
+      "epoch": 0.9082969432314411,
+      "grad_norm": 0.44923996925354004,
+      "learning_rate": 0.00012138244650689714,
+      "loss": 0.4507625102996826,
+      "step": 260
+    },
+    {
+      "epoch": 0.9432314410480349,
+      "grad_norm": 0.4775308072566986,
+      "learning_rate": 0.00011581145164313307,
+      "loss": 0.4381150722503662,
+      "step": 270
+    },
+    {
+      "epoch": 0.9781659388646288,
+      "grad_norm": 0.3662133812904358,
+      "learning_rate": 0.000110189624969195,
+      "loss": 0.4980125427246094,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 574,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 3744560261514240.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-287/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484bee6acc6c6f03f9c73fe3959d53a95a69f1c976678fc892714dc3eb69191b
+size 5713

checkpoint-574/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-574/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen2ForCausalLM",
+    "parent_library": "transformers.models.qwen2.modeling_qwen2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen2.5-coder-1.5b-instruct-bnb-4bit",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-574/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee85b59cc879e70923229a5c5e7e5a29c53953d5b768a78d15b2a33246a0543e
+size 73911112

checkpoint-574/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-574/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51dd7e4502b941dfa41c3cbc33fc32480cbd115662067326616c182eeaf2156f
+size 37974661

checkpoint-574/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
+size 14645

checkpoint-574/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52c866b78eac15c6b333969f565f2125472b9d1626e7c772b31897f849abb54
+size 1383

checkpoint-574/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99ab606fd80a186a5f0b78e5d3575d857e0c7f8ca5651a7608159f931239312c
+size 1465

checkpoint-574/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

checkpoint-574/tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoint-574/trainer_state.json

@@ -0,0 +1,433 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 574,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034934497816593885,
+      "grad_norm": 1.8211296796798706,
+      "learning_rate": 9e-05,
+      "loss": 3.1205413818359373,
+      "step": 10
+    },
+    {
+      "epoch": 0.06986899563318777,
+      "grad_norm": 2.2983880043029785,
+      "learning_rate": 0.00019,
+      "loss": 1.7317464828491211,
+      "step": 20
+    },
+    {
+      "epoch": 0.10480349344978165,
+      "grad_norm": 0.7729952335357666,
+      "learning_rate": 0.00019986979101058972,
+      "loss": 0.8218430519104004,
+      "step": 30
+    },
+    {
+      "epoch": 0.13973799126637554,
+      "grad_norm": 0.7794175744056702,
+      "learning_rate": 0.00019942012118204737,
+      "loss": 0.6791059017181397,
+      "step": 40
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "grad_norm": 0.6147348880767822,
+      "learning_rate": 0.0001986508282827419,
+      "loss": 0.5647100448608399,
+      "step": 50
+    },
+    {
+      "epoch": 0.2096069868995633,
+      "grad_norm": 0.5721135139465332,
+      "learning_rate": 0.0001975643854917025,
+      "loss": 0.4464299201965332,
+      "step": 60
+    },
+    {
+      "epoch": 0.2445414847161572,
+      "grad_norm": 0.4910798668861389,
+      "learning_rate": 0.00019616428558460634,
+      "loss": 0.5486050605773926,
+      "step": 70
+    },
+    {
+      "epoch": 0.2794759825327511,
+      "grad_norm": 0.4786812365055084,
+      "learning_rate": 0.00019445502970494787,
+      "loss": 0.6309103965759277,
+      "step": 80
+    },
+    {
+      "epoch": 0.314410480349345,
+      "grad_norm": 0.3899824321269989,
+      "learning_rate": 0.00019244211289343397,
+      "loss": 0.47461185455322263,
+      "step": 90
+    },
+    {
+      "epoch": 0.34934497816593885,
+      "grad_norm": 0.21079467236995697,
+      "learning_rate": 0.00019013200642212545,
+      "loss": 0.41464600563049314,
+      "step": 100
+    },
+    {
+      "epoch": 0.38427947598253276,
+      "grad_norm": 0.42337626218795776,
+      "learning_rate": 0.00018753213699011876,
+      "loss": 0.4927196979522705,
+      "step": 110
+    },
+    {
+      "epoch": 0.4192139737991266,
+      "grad_norm": 0.4860546588897705,
+      "learning_rate": 0.00018465086284765093,
+      "loss": 0.4953155040740967,
+      "step": 120
+    },
+    {
+      "epoch": 0.45414847161572053,
+      "grad_norm": 0.5280138850212097,
+      "learning_rate": 0.0001814974469253861,
+      "loss": 0.3739574432373047,
+      "step": 130
+    },
+    {
+      "epoch": 0.4890829694323144,
+      "grad_norm": 0.3762610852718353,
+      "learning_rate": 0.000178082027055269,
+      "loss": 0.5111323833465576,
+      "step": 140
+    },
+    {
+      "epoch": 0.5240174672489083,
+      "grad_norm": 0.5376149415969849,
+      "learning_rate": 0.00017441558337868198,
+      "loss": 0.5593331813812256,
+      "step": 150
+    },
+    {
+      "epoch": 0.5589519650655022,
+      "grad_norm": 0.472368448972702,
+      "learning_rate": 0.00017050990304668423,
+      "loss": 0.5056246757507324,
+      "step": 160
+    },
+    {
+      "epoch": 0.5938864628820961,
+      "grad_norm": 0.44528254866600037,
+      "learning_rate": 0.00016637754232581698,
+      "loss": 0.4254063606262207,
+      "step": 170
+    },
+    {
+      "epoch": 0.62882096069869,
+      "grad_norm": 0.38811150193214417,
+      "learning_rate": 0.0001620317862313006,
+      "loss": 0.5141812324523926,
+      "step": 180
+    },
+    {
+      "epoch": 0.6637554585152838,
+      "grad_norm": 0.5775936841964722,
+      "learning_rate": 0.00015748660581739655,
+      "loss": 0.49105257987976075,
+      "step": 190
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 0.47975367307662964,
+      "learning_rate": 0.0001527566132622413,
+      "loss": 0.5170726299285888,
+      "step": 200
+    },
+    {
+      "epoch": 0.7336244541484717,
+      "grad_norm": 0.3569624125957489,
+      "learning_rate": 0.0001478570148915483,
+      "loss": 0.42121267318725586,
+      "step": 210
+    },
+    {
+      "epoch": 0.7685589519650655,
+      "grad_norm": 0.5059508085250854,
+      "learning_rate": 0.0001428035622922009,
+      "loss": 0.41593084335327146,
+      "step": 220
+    },
+    {
+      "epoch": 0.8034934497816594,
+      "grad_norm": 0.45586642622947693,
+      "learning_rate": 0.0001376125016728996,
+      "loss": 0.38859803676605226,
+      "step": 230
+    },
+    {
+      "epoch": 0.8384279475982532,
+      "grad_norm": 0.41792041063308716,
+      "learning_rate": 0.00013230052163466335,
+      "loss": 0.4688732147216797,
+      "step": 240
+    },
+    {
+      "epoch": 0.8733624454148472,
+      "grad_norm": 0.46951380372047424,
+      "learning_rate": 0.0001268846995190953,
+      "loss": 0.4584070682525635,
+      "step": 250
+    },
+    {
+      "epoch": 0.9082969432314411,
+      "grad_norm": 0.44923996925354004,
+      "learning_rate": 0.00012138244650689714,
+      "loss": 0.4507625102996826,
+      "step": 260
+    },
+    {
+      "epoch": 0.9432314410480349,
+      "grad_norm": 0.4775308072566986,
+      "learning_rate": 0.00011581145164313307,
+      "loss": 0.4381150722503662,
+      "step": 270
+    },
+    {
+      "epoch": 0.9781659388646288,
+      "grad_norm": 0.3662133812904358,
+      "learning_rate": 0.000110189624969195,
+      "loss": 0.4980125427246094,
+      "step": 280
+    },
+    {
+      "epoch": 1.010480349344978,
+      "grad_norm": 0.1824927031993866,
+      "learning_rate": 0.00010453503994429279,
+      "loss": 0.3719043254852295,
+      "step": 290
+    },
+    {
+      "epoch": 1.045414847161572,
+      "grad_norm": 0.3003326654434204,
+      "learning_rate": 9.886587534157678e-05,
+      "loss": 0.39989519119262695,
+      "step": 300
+    },
+    {
+      "epoch": 1.080349344978166,
+      "grad_norm": 0.531202495098114,
+      "learning_rate": 9.32003568056896e-05,
+      "loss": 0.32967467308044435,
+      "step": 310
+    },
+    {
+      "epoch": 1.1152838427947598,
+      "grad_norm": 0.4517218768596649,
+      "learning_rate": 8.755669825963159e-05,
+      "loss": 0.3558018445968628,
+      "step": 320
+    },
+    {
+      "epoch": 1.1502183406113538,
+      "grad_norm": 0.5482302308082581,
+      "learning_rate": 8.19530433493105e-05,
+      "loss": 0.38756818771362306,
+      "step": 330
+    },
+    {
+      "epoch": 1.1851528384279475,
+      "grad_norm": 0.5365656614303589,
+      "learning_rate": 7.640740711402266e-05,
+      "loss": 0.33413424491882326,
+      "step": 340
+    },
+    {
+      "epoch": 1.2200873362445415,
+      "grad_norm": 0.5340099930763245,
+      "learning_rate": 7.093761807038802e-05,
+      "loss": 0.43075904846191404,
+      "step": 350
+    },
+    {
+      "epoch": 1.2550218340611354,
+      "grad_norm": 0.4649604558944702,
+      "learning_rate": 6.556126089593226e-05,
+      "loss": 0.42152748107910154,
+      "step": 360
+    },
+    {
+      "epoch": 1.2899563318777292,
+      "grad_norm": 0.5258662104606628,
+      "learning_rate": 6.029561989658058e-05,
+      "loss": 0.3724403381347656,
+      "step": 370
+    },
+    {
+      "epoch": 1.3248908296943231,
+      "grad_norm": 0.48639678955078125,
+      "learning_rate": 5.515762343980757e-05,
+      "loss": 0.37346906661987306,
+      "step": 380
+    },
+    {
+      "epoch": 1.359825327510917,
+      "grad_norm": 0.505720853805542,
+      "learning_rate": 5.0163789532084785e-05,
+      "loss": 0.3663132667541504,
+      "step": 390
+    },
+    {
+      "epoch": 1.3947598253275109,
+      "grad_norm": 0.4511260688304901,
+      "learning_rate": 4.533017271558631e-05,
+      "loss": 0.4028172016143799,
+      "step": 400
+    },
+    {
+      "epoch": 1.4296943231441048,
+      "grad_norm": 0.36770346760749817,
+      "learning_rate": 4.067231245487331e-05,
+      "loss": 0.28973219394683836,
+      "step": 410
+    },
+    {
+      "epoch": 1.4646288209606988,
+      "grad_norm": 0.5649269819259644,
+      "learning_rate": 3.6205183179488034e-05,
+      "loss": 0.3343945503234863,
+      "step": 420
+    },
+    {
+      "epoch": 1.4995633187772925,
+      "grad_norm": 0.5703375339508057,
+      "learning_rate": 3.1943146143063175e-05,
+      "loss": 0.3596197128295898,
+      "step": 430
+    },
+    {
+      "epoch": 1.5344978165938865,
+      "grad_norm": 0.5321503281593323,
+      "learning_rate": 2.7899903253714488e-05,
+      "loss": 0.3965036392211914,
+      "step": 440
+    },
+    {
+      "epoch": 1.5694323144104803,
+      "grad_norm": 0.5592755079269409,
+      "learning_rate": 2.4088453024145074e-05,
+      "loss": 0.3017162084579468,
+      "step": 450
+    },
+    {
+      "epoch": 1.6043668122270742,
+      "grad_norm": 0.5473719835281372,
+      "learning_rate": 2.052104878307709e-05,
+      "loss": 0.36124472618103026,
+      "step": 460
+    },
+    {
+      "epoch": 1.6393013100436682,
+      "grad_norm": 0.41305872797966003,
+      "learning_rate": 1.7209159282355047e-05,
+      "loss": 0.34646024703979494,
+      "step": 470
+    },
+    {
+      "epoch": 1.6742358078602622,
+      "grad_norm": 0.24601048231124878,
+      "learning_rate": 1.4163431826364138e-05,
+      "loss": 0.37380959987640383,
+      "step": 480
+    },
+    {
+      "epoch": 1.709170305676856,
+      "grad_norm": 0.5165665149688721,
+      "learning_rate": 1.1393658042298361e-05,
+      "loss": 0.34536712169647216,
+      "step": 490
+    },
+    {
+      "epoch": 1.7441048034934497,
+      "grad_norm": 0.5911356806755066,
+      "learning_rate": 8.908742401321701e-06,
+      "loss": 0.28776962757110597,
+      "step": 500
+    },
+    {
+      "epoch": 1.7790393013100436,
+      "grad_norm": 0.48452237248420715,
+      "learning_rate": 6.7166735918234744e-06,
+      "loss": 0.3274099349975586,
+      "step": 510
+    },
+    {
+      "epoch": 1.8139737991266376,
+      "grad_norm": 0.5194221138954163,
+      "learning_rate": 4.824498836799285e-06,
+      "loss": 0.42140350341796873,
+      "step": 520
+    },
+    {
+      "epoch": 1.8489082969432316,
+      "grad_norm": 0.4017932415008545,
+      "learning_rate": 3.2383012379234024e-06,
+      "loss": 0.32117505073547364,
+      "step": 530
+    },
+    {
+      "epoch": 1.8838427947598253,
+      "grad_norm": 0.5720022916793823,
+      "learning_rate": 1.9631802191490744e-06,
+      "loss": 0.3702544212341309,
+      "step": 540
+    },
+    {
+      "epoch": 1.9187772925764193,
+      "grad_norm": 0.42618224024772644,
+      "learning_rate": 1.003235132707725e-06,
+      "loss": 0.40667200088500977,
+      "step": 550
+    },
+    {
+      "epoch": 1.953711790393013,
+      "grad_norm": 0.5558740496635437,
+      "learning_rate": 3.615520802118244e-07,
+      "loss": 0.3302525281906128,
+      "step": 560
+    },
+    {
+      "epoch": 1.988646288209607,
+      "grad_norm": 0.5960554480552673,
+      "learning_rate": 4.019399122991985e-08,
+      "loss": 0.3490064859390259,
+      "step": 570
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 574,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7489120523028480.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-574/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484bee6acc6c6f03f9c73fe3959d53a95a69f1c976678fc892714dc3eb69191b
+size 5713

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea43b288542655d72d632195ab9b58ca2cd9532c292bf6667827ce899ad196bc
+size 11422082

tokenizer_config.json

@@ -0,0 +1,202 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}