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-17/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-34/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-51/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+model_name: track_b_sft
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for track_b_sft
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B).
+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
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/dumbal/huggingface/runs/xwrn72zo) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.18.1
+- TRL: 0.28.0
+- Transformers: 5.2.0
+- Pytorch: 2.9.1
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "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": 0.05,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_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 sha256:79fb2ad20d7abccef47d883b0ff0b0696e8fc63fdb370164fb3afb96d7ae7121
+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-17/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-17/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "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": 0.05,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-17/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa0db9b530af1a0fd56d8f501c9997353d5c4ff2774854dbd819cc0c6dcde8a
+size 73911112

checkpoint-17/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-17/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9111c762051cc608076f518ba836541b99aeae4e5c40d498b2af0687091b58d6
+size 148053627

checkpoint-17/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c78ceb8504ea85e58ae8b9bc73a01f21dca9ceba014d587d1a71dd24805d37e
+size 14645

checkpoint-17/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bd207a74c468d5e9c5de14c476cac714458bb63790e26052924d5e85022225
+size 1383

checkpoint-17/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d69dd761a8eafde257f8143032e4447e6e0ee7449011ec15c8f90e85821296e9
+size 1465

checkpoint-17/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-17/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-17/trainer_state.json

@@ -0,0 +1,204 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 17,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2623544037342072,
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.19557932019233704,
+      "learning_rate": 0.0,
+      "loss": 1.363303303718567,
+      "mean_token_accuracy": 0.6967771947383881,
+      "num_tokens": 8983.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.2696461975574493,
+      "epoch": 0.12307692307692308,
+      "grad_norm": 0.2623090445995331,
+      "learning_rate": 0.0001,
+      "loss": 1.3970271348953247,
+      "mean_token_accuracy": 0.7032225728034973,
+      "num_tokens": 15469.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.351563960313797,
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.2595767080783844,
+      "learning_rate": 0.0002,
+      "loss": 1.438194990158081,
+      "mean_token_accuracy": 0.6762479990720749,
+      "num_tokens": 23136.0,
+      "step": 3
+    },
+    {
+      "entropy": 1.156097874045372,
+      "epoch": 0.24615384615384617,
+      "grad_norm": 0.9452286958694458,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 1.191060185432434,
+      "mean_token_accuracy": 0.7312490344047546,
+      "num_tokens": 31431.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.2470719814300537,
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.29575249552726746,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.2078289985656738,
+      "mean_token_accuracy": 0.7162232249975204,
+      "num_tokens": 39311.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.3020514845848083,
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.12131688743829727,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 1.236517310142517,
+      "mean_token_accuracy": 0.7079942375421524,
+      "num_tokens": 46157.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.1494204998016357,
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.07860170304775238,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 1.0905468463897705,
+      "mean_token_accuracy": 0.74454265832901,
+      "num_tokens": 55535.0,
+      "step": 7
+    },
+    {
+      "entropy": 1.0420133769512177,
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.09150254726409912,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 1.0026195049285889,
+      "mean_token_accuracy": 0.7577853351831436,
+      "num_tokens": 63422.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.0447807163000107,
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.10369911789894104,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 1.0252422094345093,
+      "mean_token_accuracy": 0.7560650110244751,
+      "num_tokens": 70555.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.0285034626722336,
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.11572559177875519,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.052419900894165,
+      "mean_token_accuracy": 0.7432190179824829,
+      "num_tokens": 78003.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0061500668525696,
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.10965128242969513,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 0.9987847805023193,
+      "mean_token_accuracy": 0.7628708183765411,
+      "num_tokens": 86065.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.0449193269014359,
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.10073477029800415,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 1.0622799396514893,
+      "mean_token_accuracy": 0.746578574180603,
+      "num_tokens": 93482.0,
+      "step": 12
+    },
+    {
+      "entropy": 0.8957007825374603,
+      "epoch": 0.8,
+      "grad_norm": 0.10005328059196472,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 0.8889887928962708,
+      "mean_token_accuracy": 0.77289679646492,
+      "num_tokens": 100654.0,
+      "step": 13
+    },
+    {
+      "entropy": 0.9818997383117676,
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.12628009915351868,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 0.976428210735321,
+      "mean_token_accuracy": 0.7596915662288666,
+      "num_tokens": 108091.0,
+      "step": 14
+    },
+    {
+      "entropy": 0.9654281437397003,
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.11806830018758774,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 0.9671178460121155,
+      "mean_token_accuracy": 0.7701253145933151,
+      "num_tokens": 114707.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.9159971326589584,
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.09751465171575546,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.902397632598877,
+      "mean_token_accuracy": 0.7794631719589233,
+      "num_tokens": 121769.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.1713899374008179,
+      "epoch": 1.0,
+      "grad_norm": 0.5108214020729065,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.1008179187774658,
+      "mean_token_accuracy": 0.7128027677536011,
+      "num_tokens": 122059.0,
+      "step": 17
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 51,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1465581970962432.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-17/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2050cc34f19877546e9181667805ad821ca9a4aa7a4c3b14ccf1db53d804983
+size 5649

checkpoint-34/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-34/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "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": 0.05,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-34/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d97ccd85fc0c1dff7672dde2bb53b458f2869269ad0732801955564f7a81de8
+size 73911112

checkpoint-34/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-34/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9efa1ad52dc915c60117be1e95f28d6fa0dfba76b0386737b2802278e7ff1c
+size 148053627

checkpoint-34/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d335de884d3ea182ac1ea3f3d8cbc3d115c8bc06b55e71fb1d361a86db8384ac
+size 14645

checkpoint-34/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:227e3caad3f787fbe810fbac3c378957e1394c039f30869d94e84d08288a0af5
+size 1383

checkpoint-34/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2cbd54157d44da95bf4642583f9c9cb3618e2d2200ddade24b33b5ed135810f
+size 1465

checkpoint-34/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-34/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-34/trainer_state.json

@@ -0,0 +1,374 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 34,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2623544037342072,
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.19557932019233704,
+      "learning_rate": 0.0,
+      "loss": 1.363303303718567,
+      "mean_token_accuracy": 0.6967771947383881,
+      "num_tokens": 8983.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.2696461975574493,
+      "epoch": 0.12307692307692308,
+      "grad_norm": 0.2623090445995331,
+      "learning_rate": 0.0001,
+      "loss": 1.3970271348953247,
+      "mean_token_accuracy": 0.7032225728034973,
+      "num_tokens": 15469.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.351563960313797,
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.2595767080783844,
+      "learning_rate": 0.0002,
+      "loss": 1.438194990158081,
+      "mean_token_accuracy": 0.6762479990720749,
+      "num_tokens": 23136.0,
+      "step": 3
+    },
+    {
+      "entropy": 1.156097874045372,
+      "epoch": 0.24615384615384617,
+      "grad_norm": 0.9452286958694458,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 1.191060185432434,
+      "mean_token_accuracy": 0.7312490344047546,
+      "num_tokens": 31431.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.2470719814300537,
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.29575249552726746,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.2078289985656738,
+      "mean_token_accuracy": 0.7162232249975204,
+      "num_tokens": 39311.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.3020514845848083,
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.12131688743829727,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 1.236517310142517,
+      "mean_token_accuracy": 0.7079942375421524,
+      "num_tokens": 46157.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.1494204998016357,
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.07860170304775238,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 1.0905468463897705,
+      "mean_token_accuracy": 0.74454265832901,
+      "num_tokens": 55535.0,
+      "step": 7
+    },
+    {
+      "entropy": 1.0420133769512177,
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.09150254726409912,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 1.0026195049285889,
+      "mean_token_accuracy": 0.7577853351831436,
+      "num_tokens": 63422.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.0447807163000107,
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.10369911789894104,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 1.0252422094345093,
+      "mean_token_accuracy": 0.7560650110244751,
+      "num_tokens": 70555.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.0285034626722336,
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.11572559177875519,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.052419900894165,
+      "mean_token_accuracy": 0.7432190179824829,
+      "num_tokens": 78003.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0061500668525696,
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.10965128242969513,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 0.9987847805023193,
+      "mean_token_accuracy": 0.7628708183765411,
+      "num_tokens": 86065.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.0449193269014359,
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.10073477029800415,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 1.0622799396514893,
+      "mean_token_accuracy": 0.746578574180603,
+      "num_tokens": 93482.0,
+      "step": 12
+    },
+    {
+      "entropy": 0.8957007825374603,
+      "epoch": 0.8,
+      "grad_norm": 0.10005328059196472,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 0.8889887928962708,
+      "mean_token_accuracy": 0.77289679646492,
+      "num_tokens": 100654.0,
+      "step": 13
+    },
+    {
+      "entropy": 0.9818997383117676,
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.12628009915351868,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 0.976428210735321,
+      "mean_token_accuracy": 0.7596915662288666,
+      "num_tokens": 108091.0,
+      "step": 14
+    },
+    {
+      "entropy": 0.9654281437397003,
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.11806830018758774,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 0.9671178460121155,
+      "mean_token_accuracy": 0.7701253145933151,
+      "num_tokens": 114707.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.9159971326589584,
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.09751465171575546,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.902397632598877,
+      "mean_token_accuracy": 0.7794631719589233,
+      "num_tokens": 121769.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.1713899374008179,
+      "epoch": 1.0,
+      "grad_norm": 0.5108214020729065,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.1008179187774658,
+      "mean_token_accuracy": 0.7128027677536011,
+      "num_tokens": 122059.0,
+      "step": 17
+    },
+    {
+      "entropy": 0.9143469482660294,
+      "epoch": 1.0615384615384615,
+      "grad_norm": 0.08762291073799133,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.8315602540969849,
+      "mean_token_accuracy": 0.793931856751442,
+      "num_tokens": 128993.0,
+      "step": 18
+    },
+    {
+      "entropy": 0.8749453127384186,
+      "epoch": 1.123076923076923,
+      "grad_norm": 0.08239830285310745,
+      "learning_rate": 0.00015183925683105254,
+      "loss": 0.8309834003448486,
+      "mean_token_accuracy": 0.7881838083267212,
+      "num_tokens": 137231.0,
+      "step": 19
+    },
+    {
+      "entropy": 0.8598180264234543,
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.08933497220277786,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.8326812982559204,
+      "mean_token_accuracy": 0.789072722196579,
+      "num_tokens": 145190.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9529785364866257,
+      "epoch": 1.2461538461538462,
+      "grad_norm": 0.10007654130458832,
+      "learning_rate": 0.00014047833431223938,
+      "loss": 0.9316624999046326,
+      "mean_token_accuracy": 0.7664911448955536,
+      "num_tokens": 152202.0,
+      "step": 21
+    },
+    {
+      "entropy": 0.7975367158651352,
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.097578264772892,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.7583404779434204,
+      "mean_token_accuracy": 0.8191335052251816,
+      "num_tokens": 158331.0,
+      "step": 22
+    },
+    {
+      "entropy": 0.8262939751148224,
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.08703760802745819,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 0.8296029567718506,
+      "mean_token_accuracy": 0.7906320244073868,
+      "num_tokens": 166002.0,
+      "step": 23
+    },
+    {
+      "entropy": 0.9157162606716156,
+      "epoch": 1.4307692307692308,
+      "grad_norm": 0.09159163385629654,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.9092485308647156,
+      "mean_token_accuracy": 0.7690109759569168,
+      "num_tokens": 175547.0,
+      "step": 24
+    },
+    {
+      "entropy": 0.7814479619264603,
+      "epoch": 1.4923076923076923,
+      "grad_norm": 0.0804533138871193,
+      "learning_rate": 0.00011595998950333793,
+      "loss": 0.7761488556861877,
+      "mean_token_accuracy": 0.7984755784273148,
+      "num_tokens": 184577.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.7985701262950897,
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.0917685404419899,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 0.7678935527801514,
+      "mean_token_accuracy": 0.8032983243465424,
+      "num_tokens": 191871.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.9452711939811707,
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.10309547930955887,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.9123054146766663,
+      "mean_token_accuracy": 0.7641141563653946,
+      "num_tokens": 199434.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.9179778099060059,
+      "epoch": 1.676923076923077,
+      "grad_norm": 0.0981035828590393,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.8683165311813354,
+      "mean_token_accuracy": 0.7796975672245026,
+      "num_tokens": 206254.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.9250332564115524,
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.08907375484704971,
+      "learning_rate": 9.039769740923183e-05,
+      "loss": 0.9016717672348022,
+      "mean_token_accuracy": 0.7748660296201706,
+      "num_tokens": 213583.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.8822590410709381,
+      "epoch": 1.8,
+      "grad_norm": 0.09369569271802902,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 0.8634146451950073,
+      "mean_token_accuracy": 0.7857015281915665,
+      "num_tokens": 220995.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8900642246007919,
+      "epoch": 1.8615384615384616,
+      "grad_norm": 0.1084684282541275,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.9049892425537109,
+      "mean_token_accuracy": 0.7676405757665634,
+      "num_tokens": 228050.0,
+      "step": 31
+    },
+    {
+      "entropy": 0.8679154813289642,
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.09301979839801788,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 0.8593922257423401,
+      "mean_token_accuracy": 0.7785892337560654,
+      "num_tokens": 235526.0,
+      "step": 32
+    },
+    {
+      "entropy": 0.8450447171926498,
+      "epoch": 1.9846153846153847,
+      "grad_norm": 0.0842856764793396,
+      "learning_rate": 6.546349455786926e-05,
+      "loss": 0.8173251152038574,
+      "mean_token_accuracy": 0.7973018437623978,
+      "num_tokens": 243742.0,
+      "step": 33
+    },
+    {
+      "entropy": 0.8048986196517944,
+      "epoch": 2.0,
+      "grad_norm": 0.3837374150753021,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 0.6818726658821106,
+      "mean_token_accuracy": 0.8026666641235352,
+      "num_tokens": 244118.0,
+      "step": 34
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 51,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2955225949673472.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-34/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2050cc34f19877546e9181667805ad821ca9a4aa7a4c3b14ccf1db53d804983
+size 5649

checkpoint-51/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Coder-1.5B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

checkpoint-51/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B",
+  "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": 0.05,
+  "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": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-51/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fb2ad20d7abccef47d883b0ff0b0696e8fc63fdb370164fb3afb96d7ae7121
+size 73911112

checkpoint-51/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-51/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be7f0a5c913ca3304be1b18ea4a47e57cd7e9303da3ba23b1a9e0a03d97210f
+size 148053627

checkpoint-51/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d867bbb84fbf94ff822fd0b2d98080c060ff7f1ce3872a39cd320d7d27fd85bc
+size 14645

checkpoint-51/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1a5d19496e5d4bf9c5cc60fab70c6757fcb313a464c4ebfc323d888d8d878c
+size 1383

checkpoint-51/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f782d16f24cf09e5acd64560a755743c0eb6def028416fb8eb8030665f056d00
+size 1465

checkpoint-51/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

checkpoint-51/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-51/trainer_state.json

@@ -0,0 +1,544 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 51,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2623544037342072,
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.19557932019233704,
+      "learning_rate": 0.0,
+      "loss": 1.363303303718567,
+      "mean_token_accuracy": 0.6967771947383881,
+      "num_tokens": 8983.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.2696461975574493,
+      "epoch": 0.12307692307692308,
+      "grad_norm": 0.2623090445995331,
+      "learning_rate": 0.0001,
+      "loss": 1.3970271348953247,
+      "mean_token_accuracy": 0.7032225728034973,
+      "num_tokens": 15469.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.351563960313797,
+      "epoch": 0.18461538461538463,
+      "grad_norm": 0.2595767080783844,
+      "learning_rate": 0.0002,
+      "loss": 1.438194990158081,
+      "mean_token_accuracy": 0.6762479990720749,
+      "num_tokens": 23136.0,
+      "step": 3
+    },
+    {
+      "entropy": 1.156097874045372,
+      "epoch": 0.24615384615384617,
+      "grad_norm": 0.9452286958694458,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 1.191060185432434,
+      "mean_token_accuracy": 0.7312490344047546,
+      "num_tokens": 31431.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.2470719814300537,
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.29575249552726746,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.2078289985656738,
+      "mean_token_accuracy": 0.7162232249975204,
+      "num_tokens": 39311.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.3020514845848083,
+      "epoch": 0.36923076923076925,
+      "grad_norm": 0.12131688743829727,
+      "learning_rate": 0.00019815591569910654,
+      "loss": 1.236517310142517,
+      "mean_token_accuracy": 0.7079942375421524,
+      "num_tokens": 46157.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.1494204998016357,
+      "epoch": 0.4307692307692308,
+      "grad_norm": 0.07860170304775238,
+      "learning_rate": 0.00019672948630390294,
+      "loss": 1.0905468463897705,
+      "mean_token_accuracy": 0.74454265832901,
+      "num_tokens": 55535.0,
+      "step": 7
+    },
+    {
+      "entropy": 1.0420133769512177,
+      "epoch": 0.49230769230769234,
+      "grad_norm": 0.09150254726409912,
+      "learning_rate": 0.00019490557470106686,
+      "loss": 1.0026195049285889,
+      "mean_token_accuracy": 0.7577853351831436,
+      "num_tokens": 63422.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.0447807163000107,
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.10369911789894104,
+      "learning_rate": 0.0001926916757346022,
+      "loss": 1.0252422094345093,
+      "mean_token_accuracy": 0.7560650110244751,
+      "num_tokens": 70555.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.0285034626722336,
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.11572559177875519,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 1.052419900894165,
+      "mean_token_accuracy": 0.7432190179824829,
+      "num_tokens": 78003.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0061500668525696,
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.10965128242969513,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 0.9987847805023193,
+      "mean_token_accuracy": 0.7628708183765411,
+      "num_tokens": 86065.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.0449193269014359,
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.10073477029800415,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 1.0622799396514893,
+      "mean_token_accuracy": 0.746578574180603,
+      "num_tokens": 93482.0,
+      "step": 12
+    },
+    {
+      "entropy": 0.8957007825374603,
+      "epoch": 0.8,
+      "grad_norm": 0.10005328059196472,
+      "learning_rate": 0.00018014136218679567,
+      "loss": 0.8889887928962708,
+      "mean_token_accuracy": 0.77289679646492,
+      "num_tokens": 100654.0,
+      "step": 13
+    },
+    {
+      "entropy": 0.9818997383117676,
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.12628009915351868,
+      "learning_rate": 0.00017614459583691346,
+      "loss": 0.976428210735321,
+      "mean_token_accuracy": 0.7596915662288666,
+      "num_tokens": 108091.0,
+      "step": 14
+    },
+    {
+      "entropy": 0.9654281437397003,
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.11806830018758774,
+      "learning_rate": 0.00017183493500977278,
+      "loss": 0.9671178460121155,
+      "mean_token_accuracy": 0.7701253145933151,
+      "num_tokens": 114707.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.9159971326589584,
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.09751465171575546,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.902397632598877,
+      "mean_token_accuracy": 0.7794631719589233,
+      "num_tokens": 121769.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.1713899374008179,
+      "epoch": 1.0,
+      "grad_norm": 0.5108214020729065,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 1.1008179187774658,
+      "mean_token_accuracy": 0.7128027677536011,
+      "num_tokens": 122059.0,
+      "step": 17
+    },
+    {
+      "entropy": 0.9143469482660294,
+      "epoch": 1.0615384615384615,
+      "grad_norm": 0.08762291073799133,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.8315602540969849,
+      "mean_token_accuracy": 0.793931856751442,
+      "num_tokens": 128993.0,
+      "step": 18
+    },
+    {
+      "entropy": 0.8749453127384186,
+      "epoch": 1.123076923076923,
+      "grad_norm": 0.08239830285310745,
+      "learning_rate": 0.00015183925683105254,
+      "loss": 0.8309834003448486,
+      "mean_token_accuracy": 0.7881838083267212,
+      "num_tokens": 137231.0,
+      "step": 19
+    },
+    {
+      "entropy": 0.8598180264234543,
+      "epoch": 1.1846153846153846,
+      "grad_norm": 0.08933497220277786,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.8326812982559204,
+      "mean_token_accuracy": 0.789072722196579,
+      "num_tokens": 145190.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.9529785364866257,
+      "epoch": 1.2461538461538462,
+      "grad_norm": 0.10007654130458832,
+      "learning_rate": 0.00014047833431223938,
+      "loss": 0.9316624999046326,
+      "mean_token_accuracy": 0.7664911448955536,
+      "num_tokens": 152202.0,
+      "step": 21
+    },
+    {
+      "entropy": 0.7975367158651352,
+      "epoch": 1.3076923076923077,
+      "grad_norm": 0.097578264772892,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.7583404779434204,
+      "mean_token_accuracy": 0.8191335052251816,
+      "num_tokens": 158331.0,
+      "step": 22
+    },
+    {
+      "entropy": 0.8262939751148224,
+      "epoch": 1.3692307692307693,
+      "grad_norm": 0.08703760802745819,
+      "learning_rate": 0.00012845275866310324,
+      "loss": 0.8296029567718506,
+      "mean_token_accuracy": 0.7906320244073868,
+      "num_tokens": 166002.0,
+      "step": 23
+    },
+    {
+      "entropy": 0.9157162606716156,
+      "epoch": 1.4307692307692308,
+      "grad_norm": 0.09159163385629654,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.9092485308647156,
+      "mean_token_accuracy": 0.7690109759569168,
+      "num_tokens": 175547.0,
+      "step": 24
+    },
+    {
+      "entropy": 0.7814479619264603,
+      "epoch": 1.4923076923076923,
+      "grad_norm": 0.0804533138871193,
+      "learning_rate": 0.00011595998950333793,
+      "loss": 0.7761488556861877,
+      "mean_token_accuracy": 0.7984755784273148,
+      "num_tokens": 184577.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.7985701262950897,
+      "epoch": 1.5538461538461539,
+      "grad_norm": 0.0917685404419899,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 0.7678935527801514,
+      "mean_token_accuracy": 0.8032983243465424,
+      "num_tokens": 191871.0,
+      "step": 26
+    },
+    {
+      "entropy": 0.9452711939811707,
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.10309547930955887,
+      "learning_rate": 0.00010320515775716555,
+      "loss": 0.9123054146766663,
+      "mean_token_accuracy": 0.7641141563653946,
+      "num_tokens": 199434.0,
+      "step": 27
+    },
+    {
+      "entropy": 0.9179778099060059,
+      "epoch": 1.676923076923077,
+      "grad_norm": 0.0981035828590393,
+      "learning_rate": 9.679484224283449e-05,
+      "loss": 0.8683165311813354,
+      "mean_token_accuracy": 0.7796975672245026,
+      "num_tokens": 206254.0,
+      "step": 28
+    },
+    {
+      "entropy": 0.9250332564115524,
+      "epoch": 1.7384615384615385,
+      "grad_norm": 0.08907375484704971,
+      "learning_rate": 9.039769740923183e-05,
+      "loss": 0.9016717672348022,
+      "mean_token_accuracy": 0.7748660296201706,
+      "num_tokens": 213583.0,
+      "step": 29
+    },
+    {
+      "entropy": 0.8822590410709381,
+      "epoch": 1.8,
+      "grad_norm": 0.09369569271802902,
+      "learning_rate": 8.404001049666211e-05,
+      "loss": 0.8634146451950073,
+      "mean_token_accuracy": 0.7857015281915665,
+      "num_tokens": 220995.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8900642246007919,
+      "epoch": 1.8615384615384616,
+      "grad_norm": 0.1084684282541275,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.9049892425537109,
+      "mean_token_accuracy": 0.7676405757665634,
+      "num_tokens": 228050.0,
+      "step": 31
+    },
+    {
+      "entropy": 0.8679154813289642,
+      "epoch": 1.9230769230769231,
+      "grad_norm": 0.09301979839801788,
+      "learning_rate": 7.154724133689677e-05,
+      "loss": 0.8593922257423401,
+      "mean_token_accuracy": 0.7785892337560654,
+      "num_tokens": 235526.0,
+      "step": 32
+    },
+    {
+      "entropy": 0.8450447171926498,
+      "epoch": 1.9846153846153847,
+      "grad_norm": 0.0842856764793396,
+      "learning_rate": 6.546349455786926e-05,
+      "loss": 0.8173251152038574,
+      "mean_token_accuracy": 0.7973018437623978,
+      "num_tokens": 243742.0,
+      "step": 33
+    },
+    {
+      "entropy": 0.8048986196517944,
+      "epoch": 2.0,
+      "grad_norm": 0.3837374150753021,
+      "learning_rate": 5.952166568776062e-05,
+      "loss": 0.6818726658821106,
+      "mean_token_accuracy": 0.8026666641235352,
+      "num_tokens": 244118.0,
+      "step": 34
+    },
+    {
+      "entropy": 0.7753455340862274,
+      "epoch": 2.0615384615384613,
+      "grad_norm": 0.08415307849645615,
+      "learning_rate": 5.37461709759165e-05,
+      "loss": 0.7494256496429443,
+      "mean_token_accuracy": 0.8127170354127884,
+      "num_tokens": 250812.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.8705243319272995,
+      "epoch": 2.123076923076923,
+      "grad_norm": 0.08281857520341873,
+      "learning_rate": 4.8160743168947496e-05,
+      "loss": 0.8155778050422668,
+      "mean_token_accuracy": 0.7962700128555298,
+      "num_tokens": 259283.0,
+      "step": 36
+    },
+    {
+      "entropy": 0.8529106080532074,
+      "epoch": 2.184615384615385,
+      "grad_norm": 0.08684741705656052,
+      "learning_rate": 4.278833398778306e-05,
+      "loss": 0.8145401477813721,
+      "mean_token_accuracy": 0.7847489565610886,
+      "num_tokens": 266873.0,
+      "step": 37
+    },
+    {
+      "entropy": 0.8403101414442062,
+      "epoch": 2.246153846153846,
+      "grad_norm": 0.08266881853342056,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.7661445140838623,
+      "mean_token_accuracy": 0.7890966683626175,
+      "num_tokens": 275434.0,
+      "step": 38
+    },
+    {
+      "entropy": 0.8713241517543793,
+      "epoch": 2.3076923076923075,
+      "grad_norm": 0.10077489912509918,
+      "learning_rate": 3.276991097386831e-05,
+      "loss": 0.8386235237121582,
+      "mean_token_accuracy": 0.7867482155561447,
+      "num_tokens": 283379.0,
+      "step": 39
+    },
+    {
+      "entropy": 0.83709417283535,
+      "epoch": 2.3692307692307693,
+      "grad_norm": 0.09080053120851517,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.8067209720611572,
+      "mean_token_accuracy": 0.8016703128814697,
+      "num_tokens": 290338.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.8438597768545151,
+      "epoch": 2.430769230769231,
+      "grad_norm": 0.08650004863739014,
+      "learning_rate": 2.3855404163086558e-05,
+      "loss": 0.8423045873641968,
+      "mean_token_accuracy": 0.7904495745897293,
+      "num_tokens": 297691.0,
+      "step": 41
+    },
+    {
+      "entropy": 0.9152878075838089,
+      "epoch": 2.4923076923076923,
+      "grad_norm": 0.09586209803819656,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.852942705154419,
+      "mean_token_accuracy": 0.7787963896989822,
+      "num_tokens": 306035.0,
+      "step": 42
+    },
+    {
+      "entropy": 0.8039195388555527,
+      "epoch": 2.5538461538461537,
+      "grad_norm": 0.09025844186544418,
+      "learning_rate": 1.619118951081594e-05,
+      "loss": 0.7521865367889404,
+      "mean_token_accuracy": 0.7952634990215302,
+      "num_tokens": 312983.0,
+      "step": 43
+    },
+    {
+      "entropy": 0.823731929063797,
+      "epoch": 2.6153846153846154,
+      "grad_norm": 0.08297690749168396,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.7870848178863525,
+      "mean_token_accuracy": 0.8034364879131317,
+      "num_tokens": 320988.0,
+      "step": 44
+    },
+    {
+      "entropy": 0.7294498234987259,
+      "epoch": 2.676923076923077,
+      "grad_norm": 0.08398636430501938,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.695728063583374,
+      "mean_token_accuracy": 0.8254178762435913,
+      "num_tokens": 328225.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.8571453243494034,
+      "epoch": 2.7384615384615385,
+      "grad_norm": 0.08756409585475922,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.8280683755874634,
+      "mean_token_accuracy": 0.78800830245018,
+      "num_tokens": 336579.0,
+      "step": 46
+    },
+    {
+      "entropy": 0.7919066250324249,
+      "epoch": 2.8,
+      "grad_norm": 0.08554663509130478,
+      "learning_rate": 5.094425298933136e-06,
+      "loss": 0.7187934517860413,
+      "mean_token_accuracy": 0.8041840344667435,
+      "num_tokens": 344723.0,
+      "step": 47
+    },
+    {
+      "entropy": 0.8572646379470825,
+      "epoch": 2.8615384615384616,
+      "grad_norm": 0.09562932699918747,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.8291648030281067,
+      "mean_token_accuracy": 0.7917099297046661,
+      "num_tokens": 352382.0,
+      "step": 48
+    },
+    {
+      "entropy": 0.7069458961486816,
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.09365329891443253,
+      "learning_rate": 1.8440843008934561e-06,
+      "loss": 0.6509672999382019,
+      "mean_token_accuracy": 0.8331291377544403,
+      "num_tokens": 358675.0,
+      "step": 49
+    },
+    {
+      "entropy": 0.727226197719574,
+      "epoch": 2.9846153846153847,
+      "grad_norm": 0.08536290377378464,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.7147982716560364,
+      "mean_token_accuracy": 0.8153118640184402,
+      "num_tokens": 365917.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.6229841709136963,
+      "epoch": 3.0,
+      "grad_norm": 0.373575896024704,
+      "learning_rate": 2.054607249663665e-07,
+      "loss": 0.5710164904594421,
+      "mean_token_accuracy": 0.8725868463516235,
+      "num_tokens": 366177.0,
+      "step": 51
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 51,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 4397256174151680.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-51/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2050cc34f19877546e9181667805ad821ca9a4aa7a4c3b14ccf1db53d804983
+size 5649

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": false,
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2050cc34f19877546e9181667805ad821ca9a4aa7a4c3b14ccf1db53d804983
+size 5649