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-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1467/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+model_name: Community-Qwen2.5-7B-output
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for Community-Qwen2.5-7B-output
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.19.1
+- TRL: 1.2.0
+- Transformers: 5.5.1
+- Pytorch: 2.11.0+rocm7.2
+- Datasets: 4.8.4
+- 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 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": 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:d8d2b3a64b67283aa533682fa2499e400b6b42155068795c52b98eeef5a0bfc1
+size 80792880

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-1000/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7c3c166b244c3d0adc6975fe1d32937664110b9dcdd73c94f684b9e72d80c2
+size 80792880

checkpoint-1000/chat_template.jinja

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

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8968557a1fdedd513910ad0ce10b403ebd1b3296b1d8d599dd6147cc046d8df
+size 161810747

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c936bc4172a83a03c773a3c49dcc7cb2d90c7bcb031925ae496d0aa65351c2b0
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76af41d9e43d3e9faf28a5081b12f2b1d7ef61d24defd63d6c9fd17ea7931c83
+size 1465

checkpoint-1000/tokenizer.json

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

checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1000/trainer_state.json

@@ -0,0 +1,434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6817794443497529,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.163015019595623,
+      "epoch": 0.01704448610874382,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 2.4524998474121094,
+      "mean_token_accuracy": 0.5153323707729578,
+      "num_tokens": 132137.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.2185084584355352,
+      "epoch": 0.03408897221748764,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.000199996095299633,
+      "loss": 2.173491668701172,
+      "mean_token_accuracy": 0.5537562420964242,
+      "num_tokens": 261404.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.9352111649513244,
+      "epoch": 0.051133458326231465,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.0001997948280489004,
+      "loss": 1.8705439758300781,
+      "mean_token_accuracy": 0.5959619037806988,
+      "num_tokens": 396323.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.76205413736403,
+      "epoch": 0.06817794443497528,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 0.00019928920737019733,
+      "loss": 1.6511923217773437,
+      "mean_token_accuracy": 0.6337622724473476,
+      "num_tokens": 527358.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.4949746784381568,
+      "epoch": 0.08522243054371911,
+      "grad_norm": 0.0625,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 1.3673600769042968,
+      "mean_token_accuracy": 0.6848376739770174,
+      "num_tokens": 655447.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.4837670608237385,
+      "epoch": 0.10226691665246293,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001973719973913012,
+      "loss": 1.4141250610351563,
+      "mean_token_accuracy": 0.6836329951137304,
+      "num_tokens": 790490.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.3150090302992612,
+      "epoch": 0.11931140276120675,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019596625518199077,
+      "loss": 1.2282736968994141,
+      "mean_token_accuracy": 0.7172392677515745,
+      "num_tokens": 925069.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.3966816508676856,
+      "epoch": 0.13635588886995056,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00019426783589406642,
+      "loss": 1.3173268127441407,
+      "mean_token_accuracy": 0.7017394271492958,
+      "num_tokens": 1052891.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.2435051177628338,
+      "epoch": 0.15340037497869438,
+      "grad_norm": 0.042236328125,
+      "learning_rate": 0.00019228191935240007,
+      "loss": 1.115916519165039,
+      "mean_token_accuracy": 0.7378023877739907,
+      "num_tokens": 1184065.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.3924890440981834,
+      "epoch": 0.17044486108743823,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.00019001456218857208,
+      "loss": 1.288157958984375,
+      "mean_token_accuracy": 0.7004149560630322,
+      "num_tokens": 1313612.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.3593159637693315,
+      "epoch": 0.18748934719618204,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 0.00018747267936940722,
+      "loss": 1.2840399169921874,
+      "mean_token_accuracy": 0.7129683202505112,
+      "num_tokens": 1444287.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.2371155321784317,
+      "epoch": 0.20453383330492586,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00018466402310776708,
+      "loss": 1.1687215423583985,
+      "mean_token_accuracy": 0.73335683144629,
+      "num_tokens": 1577307.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.2478438840154558,
+      "epoch": 0.22157831941366968,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00018159715921991612,
+      "loss": 1.20022216796875,
+      "mean_token_accuracy": 0.732666322439909,
+      "num_tokens": 1711348.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.1931916671898215,
+      "epoch": 0.2386228055224135,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.00017828144100156754,
+      "loss": 1.082593002319336,
+      "mean_token_accuracy": 0.7456949570775032,
+      "num_tokens": 1842011.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.1265690931119026,
+      "epoch": 0.2556672916311573,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00017472698070228047,
+      "loss": 1.0630721282958984,
+      "mean_token_accuracy": 0.7553409574180842,
+      "num_tokens": 1976056.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.1145534914545714,
+      "epoch": 0.27271177773990113,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 0.00017094461868520622,
+      "loss": 1.0225981903076171,
+      "mean_token_accuracy": 0.7580388783663511,
+      "num_tokens": 2109389.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.25198206695728,
+      "epoch": 0.28975626384864495,
+      "grad_norm": 0.048828125,
+      "learning_rate": 0.00016694589036623988,
+      "loss": 1.194885482788086,
+      "mean_token_accuracy": 0.7303700438886881,
+      "num_tokens": 2240117.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.1865128787327557,
+      "epoch": 0.30680074995738876,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 0.0001627429910334058,
+      "loss": 1.118544158935547,
+      "mean_token_accuracy": 0.7400260034948587,
+      "num_tokens": 2364080.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.274649427868426,
+      "epoch": 0.3238452360661326,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00015834873865377077,
+      "loss": 1.1928933715820313,
+      "mean_token_accuracy": 0.7288886807858944,
+      "num_tokens": 2497166.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.1076703028334305,
+      "epoch": 0.34088972217487645,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 0.00015377653478131556,
+      "loss": 1.0115528869628907,
+      "mean_token_accuracy": 0.7560868422687054,
+      "num_tokens": 2632559.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.1313659130921587,
+      "epoch": 0.35793420828362027,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00014904032368498856,
+      "loss": 1.0595830535888673,
+      "mean_token_accuracy": 0.756401935890317,
+      "num_tokens": 2764478.0,
+      "step": 525
+    },
+    {
+      "entropy": 1.0654471471440048,
+      "epoch": 0.3749786943923641,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 0.0001441545498215912,
+      "loss": 1.0119430541992187,
+      "mean_token_accuracy": 0.768122655749321,
+      "num_tokens": 2901372.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.2444889663858338,
+      "epoch": 0.3920231805011079,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00013913411378319504,
+      "loss": 1.2215270233154296,
+      "mean_token_accuracy": 0.729380588978529,
+      "num_tokens": 3031999.0,
+      "step": 575
+    },
+    {
+      "entropy": 1.0762281655799597,
+      "epoch": 0.4090676666098517,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 0.0001339943268534414,
+      "loss": 0.9998902893066406,
+      "mean_token_accuracy": 0.768867435157299,
+      "num_tokens": 3164064.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.0626403710339218,
+      "epoch": 0.42611215271859554,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00012875086431131716,
+      "loss": 0.9624679565429688,
+      "mean_token_accuracy": 0.771867539063096,
+      "num_tokens": 3288692.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.9459870021557435,
+      "epoch": 0.44315663882733936,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.00012341971762482043,
+      "loss": 0.9064933776855468,
+      "mean_token_accuracy": 0.7910215198248625,
+      "num_tokens": 3418627.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.045862675276585,
+      "epoch": 0.4602011249360832,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.00011801714568031615,
+      "loss": 0.9381060791015625,
+      "mean_token_accuracy": 0.770117818787694,
+      "num_tokens": 3545140.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.9516787563310936,
+      "epoch": 0.477245611044827,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 0.00011255962519632081,
+      "loss": 0.8808039093017578,
+      "mean_token_accuracy": 0.7909089859575034,
+      "num_tokens": 3679692.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.9953352324664593,
+      "epoch": 0.4942900971535708,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 0.00010706380047294496,
+      "loss": 0.9232154846191406,
+      "mean_token_accuracy": 0.7844866032898427,
+      "num_tokens": 3810488.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.92748022117652,
+      "epoch": 0.5113345832623146,
+      "grad_norm": 0.07421875,
+      "learning_rate": 0.00010154643263024644,
+      "loss": 0.8504108428955078,
+      "mean_token_accuracy": 0.7934545055776835,
+      "num_tokens": 3937101.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.9793470423854888,
+      "epoch": 0.5283790693710585,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 9.602434849030745e-05,
+      "loss": 0.8816374969482422,
+      "mean_token_accuracy": 0.786624568477273,
+      "num_tokens": 4069539.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.9201436020294205,
+      "epoch": 0.5454235554798023,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 9.051438925893384e-05,
+      "loss": 0.8456056976318359,
+      "mean_token_accuracy": 0.7975382874906063,
+      "num_tokens": 4196197.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.8780001322366298,
+      "epoch": 0.5624680415885461,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.503335916348721e-05,
+      "loss": 0.7664035034179687,
+      "mean_token_accuracy": 0.8094721902906895,
+      "num_tokens": 4328551.0,
+      "step": 825
+    },
+    {
+      "entropy": 1.0318437330564485,
+      "epoch": 0.5795125276972899,
+      "grad_norm": 0.0625,
+      "learning_rate": 7.959797420349355e-05,
+      "loss": 0.9603571319580078,
+      "mean_token_accuracy": 0.7762538179755211,
+      "num_tokens": 4461738.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.001236357828602,
+      "epoch": 0.5965570138060338,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 7.422481117032823e-05,
+      "loss": 0.9705011749267578,
+      "mean_token_accuracy": 0.7822855979949236,
+      "num_tokens": 4595951.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.9190932653006166,
+      "epoch": 0.6136014999147775,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 6.893025709145718e-05,
+      "loss": 0.7840510559082031,
+      "mean_token_accuracy": 0.7955148361623288,
+      "num_tokens": 4721963.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.9409526876406744,
+      "epoch": 0.6306459860235214,
+      "grad_norm": 0.07421875,
+      "learning_rate": 6.373045925341794e-05,
+      "loss": 0.8891078948974609,
+      "mean_token_accuracy": 0.797613599896431,
+      "num_tokens": 4857248.0,
+      "step": 925
+    },
+    {
+      "entropy": 0.9927360657276586,
+      "epoch": 0.6476904721322652,
+      "grad_norm": 0.05859375,
+      "learning_rate": 5.864127595596118e-05,
+      "loss": 0.9160787963867187,
+      "mean_token_accuracy": 0.7845662014186382,
+      "num_tokens": 4990977.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.0460572233749554,
+      "epoch": 0.664734958241009,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 5.367822814754124e-05,
+      "loss": 1.0131810760498048,
+      "mean_token_accuracy": 0.7867030793055892,
+      "num_tokens": 5126029.0,
+      "step": 975
+    },
+    {
+      "entropy": 0.9399900265224278,
+      "epoch": 0.6817794443497529,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 4.885645208965779e-05,
+      "loss": 0.8525303649902344,
+      "mean_token_accuracy": 0.7958442622423172,
+      "num_tokens": 5258088.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1467,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2434124541733274e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc4c6c929872f6609871e917db76edda2422f46a78f2141949ced04b85bfae0
+size 5649

checkpoint-1467/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-1467/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1467/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8d2b3a64b67283aa533682fa2499e400b6b42155068795c52b98eeef5a0bfc1
+size 80792880

checkpoint-1467/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-1467/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091019192da312ed9e418a697ec02121b5f7a39a8916105fe484c815e0b454d0
+size 161810747

checkpoint-1467/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc78e19ad788d4b64c8d16989a877f4cd3a3faf7d582996384b33fbc482659e
+size 14645

checkpoint-1467/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20698c03b3cfc3824b3f1c419489b692cf2c43444f40387a6ced5edbdbf0b39
+size 1465

checkpoint-1467/tokenizer.json

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

checkpoint-1467/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1467/trainer_state.json

@@ -0,0 +1,614 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1467,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.163015019595623,
+      "epoch": 0.01704448610874382,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 2.4524998474121094,
+      "mean_token_accuracy": 0.5153323707729578,
+      "num_tokens": 132137.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.2185084584355352,
+      "epoch": 0.03408897221748764,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.000199996095299633,
+      "loss": 2.173491668701172,
+      "mean_token_accuracy": 0.5537562420964242,
+      "num_tokens": 261404.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.9352111649513244,
+      "epoch": 0.051133458326231465,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.0001997948280489004,
+      "loss": 1.8705439758300781,
+      "mean_token_accuracy": 0.5959619037806988,
+      "num_tokens": 396323.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.76205413736403,
+      "epoch": 0.06817794443497528,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 0.00019928920737019733,
+      "loss": 1.6511923217773437,
+      "mean_token_accuracy": 0.6337622724473476,
+      "num_tokens": 527358.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.4949746784381568,
+      "epoch": 0.08522243054371911,
+      "grad_norm": 0.0625,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 1.3673600769042968,
+      "mean_token_accuracy": 0.6848376739770174,
+      "num_tokens": 655447.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.4837670608237385,
+      "epoch": 0.10226691665246293,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001973719973913012,
+      "loss": 1.4141250610351563,
+      "mean_token_accuracy": 0.6836329951137304,
+      "num_tokens": 790490.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.3150090302992612,
+      "epoch": 0.11931140276120675,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019596625518199077,
+      "loss": 1.2282736968994141,
+      "mean_token_accuracy": 0.7172392677515745,
+      "num_tokens": 925069.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.3966816508676856,
+      "epoch": 0.13635588886995056,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00019426783589406642,
+      "loss": 1.3173268127441407,
+      "mean_token_accuracy": 0.7017394271492958,
+      "num_tokens": 1052891.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.2435051177628338,
+      "epoch": 0.15340037497869438,
+      "grad_norm": 0.042236328125,
+      "learning_rate": 0.00019228191935240007,
+      "loss": 1.115916519165039,
+      "mean_token_accuracy": 0.7378023877739907,
+      "num_tokens": 1184065.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.3924890440981834,
+      "epoch": 0.17044486108743823,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.00019001456218857208,
+      "loss": 1.288157958984375,
+      "mean_token_accuracy": 0.7004149560630322,
+      "num_tokens": 1313612.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.3593159637693315,
+      "epoch": 0.18748934719618204,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 0.00018747267936940722,
+      "loss": 1.2840399169921874,
+      "mean_token_accuracy": 0.7129683202505112,
+      "num_tokens": 1444287.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.2371155321784317,
+      "epoch": 0.20453383330492586,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00018466402310776708,
+      "loss": 1.1687215423583985,
+      "mean_token_accuracy": 0.73335683144629,
+      "num_tokens": 1577307.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.2478438840154558,
+      "epoch": 0.22157831941366968,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00018159715921991612,
+      "loss": 1.20022216796875,
+      "mean_token_accuracy": 0.732666322439909,
+      "num_tokens": 1711348.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.1931916671898215,
+      "epoch": 0.2386228055224135,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.00017828144100156754,
+      "loss": 1.082593002319336,
+      "mean_token_accuracy": 0.7456949570775032,
+      "num_tokens": 1842011.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.1265690931119026,
+      "epoch": 0.2556672916311573,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00017472698070228047,
+      "loss": 1.0630721282958984,
+      "mean_token_accuracy": 0.7553409574180842,
+      "num_tokens": 1976056.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.1145534914545714,
+      "epoch": 0.27271177773990113,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 0.00017094461868520622,
+      "loss": 1.0225981903076171,
+      "mean_token_accuracy": 0.7580388783663511,
+      "num_tokens": 2109389.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.25198206695728,
+      "epoch": 0.28975626384864495,
+      "grad_norm": 0.048828125,
+      "learning_rate": 0.00016694589036623988,
+      "loss": 1.194885482788086,
+      "mean_token_accuracy": 0.7303700438886881,
+      "num_tokens": 2240117.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.1865128787327557,
+      "epoch": 0.30680074995738876,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 0.0001627429910334058,
+      "loss": 1.118544158935547,
+      "mean_token_accuracy": 0.7400260034948587,
+      "num_tokens": 2364080.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.274649427868426,
+      "epoch": 0.3238452360661326,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00015834873865377077,
+      "loss": 1.1928933715820313,
+      "mean_token_accuracy": 0.7288886807858944,
+      "num_tokens": 2497166.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.1076703028334305,
+      "epoch": 0.34088972217487645,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 0.00015377653478131556,
+      "loss": 1.0115528869628907,
+      "mean_token_accuracy": 0.7560868422687054,
+      "num_tokens": 2632559.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.1313659130921587,
+      "epoch": 0.35793420828362027,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00014904032368498856,
+      "loss": 1.0595830535888673,
+      "mean_token_accuracy": 0.756401935890317,
+      "num_tokens": 2764478.0,
+      "step": 525
+    },
+    {
+      "entropy": 1.0654471471440048,
+      "epoch": 0.3749786943923641,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 0.0001441545498215912,
+      "loss": 1.0119430541992187,
+      "mean_token_accuracy": 0.768122655749321,
+      "num_tokens": 2901372.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.2444889663858338,
+      "epoch": 0.3920231805011079,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00013913411378319504,
+      "loss": 1.2215270233154296,
+      "mean_token_accuracy": 0.729380588978529,
+      "num_tokens": 3031999.0,
+      "step": 575
+    },
+    {
+      "entropy": 1.0762281655799597,
+      "epoch": 0.4090676666098517,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 0.0001339943268534414,
+      "loss": 0.9998902893066406,
+      "mean_token_accuracy": 0.768867435157299,
+      "num_tokens": 3164064.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.0626403710339218,
+      "epoch": 0.42611215271859554,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00012875086431131716,
+      "loss": 0.9624679565429688,
+      "mean_token_accuracy": 0.771867539063096,
+      "num_tokens": 3288692.0,
+      "step": 625
+    },
+    {
+      "entropy": 0.9459870021557435,
+      "epoch": 0.44315663882733936,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.00012341971762482043,
+      "loss": 0.9064933776855468,
+      "mean_token_accuracy": 0.7910215198248625,
+      "num_tokens": 3418627.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.045862675276585,
+      "epoch": 0.4602011249360832,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 0.00011801714568031615,
+      "loss": 0.9381060791015625,
+      "mean_token_accuracy": 0.770117818787694,
+      "num_tokens": 3545140.0,
+      "step": 675
+    },
+    {
+      "entropy": 0.9516787563310936,
+      "epoch": 0.477245611044827,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 0.00011255962519632081,
+      "loss": 0.8808039093017578,
+      "mean_token_accuracy": 0.7909089859575034,
+      "num_tokens": 3679692.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.9953352324664593,
+      "epoch": 0.4942900971535708,
+      "grad_norm": 0.051513671875,
+      "learning_rate": 0.00010706380047294496,
+      "loss": 0.9232154846191406,
+      "mean_token_accuracy": 0.7844866032898427,
+      "num_tokens": 3810488.0,
+      "step": 725
+    },
+    {
+      "entropy": 0.92748022117652,
+      "epoch": 0.5113345832623146,
+      "grad_norm": 0.07421875,
+      "learning_rate": 0.00010154643263024644,
+      "loss": 0.8504108428955078,
+      "mean_token_accuracy": 0.7934545055776835,
+      "num_tokens": 3937101.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.9793470423854888,
+      "epoch": 0.5283790693710585,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 9.602434849030745e-05,
+      "loss": 0.8816374969482422,
+      "mean_token_accuracy": 0.786624568477273,
+      "num_tokens": 4069539.0,
+      "step": 775
+    },
+    {
+      "entropy": 0.9201436020294205,
+      "epoch": 0.5454235554798023,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 9.051438925893384e-05,
+      "loss": 0.8456056976318359,
+      "mean_token_accuracy": 0.7975382874906063,
+      "num_tokens": 4196197.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.8780001322366298,
+      "epoch": 0.5624680415885461,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 8.503335916348721e-05,
+      "loss": 0.7664035034179687,
+      "mean_token_accuracy": 0.8094721902906895,
+      "num_tokens": 4328551.0,
+      "step": 825
+    },
+    {
+      "entropy": 1.0318437330564485,
+      "epoch": 0.5795125276972899,
+      "grad_norm": 0.0625,
+      "learning_rate": 7.959797420349355e-05,
+      "loss": 0.9603571319580078,
+      "mean_token_accuracy": 0.7762538179755211,
+      "num_tokens": 4461738.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.001236357828602,
+      "epoch": 0.5965570138060338,
+      "grad_norm": 0.05322265625,
+      "learning_rate": 7.422481117032823e-05,
+      "loss": 0.9705011749267578,
+      "mean_token_accuracy": 0.7822855979949236,
+      "num_tokens": 4595951.0,
+      "step": 875
+    },
+    {
+      "entropy": 0.9190932653006166,
+      "epoch": 0.6136014999147775,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 6.893025709145718e-05,
+      "loss": 0.7840510559082031,
+      "mean_token_accuracy": 0.7955148361623288,
+      "num_tokens": 4721963.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.9409526876406744,
+      "epoch": 0.6306459860235214,
+      "grad_norm": 0.07421875,
+      "learning_rate": 6.373045925341794e-05,
+      "loss": 0.8891078948974609,
+      "mean_token_accuracy": 0.797613599896431,
+      "num_tokens": 4857248.0,
+      "step": 925
+    },
+    {
+      "entropy": 0.9927360657276586,
+      "epoch": 0.6476904721322652,
+      "grad_norm": 0.05859375,
+      "learning_rate": 5.864127595596118e-05,
+      "loss": 0.9160787963867187,
+      "mean_token_accuracy": 0.7845662014186382,
+      "num_tokens": 4990977.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.0460572233749554,
+      "epoch": 0.664734958241009,
+      "grad_norm": 0.048583984375,
+      "learning_rate": 5.367822814754124e-05,
+      "loss": 1.0131810760498048,
+      "mean_token_accuracy": 0.7867030793055892,
+      "num_tokens": 5126029.0,
+      "step": 975
+    },
+    {
+      "entropy": 0.9399900265224278,
+      "epoch": 0.6817794443497529,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 4.885645208965779e-05,
+      "loss": 0.8525303649902344,
+      "mean_token_accuracy": 0.7958442622423172,
+      "num_tokens": 5258088.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.9254711728263646,
+      "epoch": 0.6988239304584967,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 4.419065319441306e-05,
+      "loss": 0.8452438354492188,
+      "mean_token_accuracy": 0.8007816936075688,
+      "num_tokens": 5389128.0,
+      "step": 1025
+    },
+    {
+      "entropy": 0.9583898686571046,
+      "epoch": 0.7158684165672405,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 3.969506117606927e-05,
+      "loss": 0.910721435546875,
+      "mean_token_accuracy": 0.7937231123447418,
+      "num_tokens": 5518384.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.9213999844761566,
+      "epoch": 0.7329129026759843,
+      "grad_norm": 0.0625,
+      "learning_rate": 3.538338665338589e-05,
+      "loss": 0.8783349609375,
+      "mean_token_accuracy": 0.7985107507556677,
+      "num_tokens": 5649311.0,
+      "step": 1075
+    },
+    {
+      "entropy": 1.0327887642104179,
+      "epoch": 0.7499573887847282,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 3.126877933508957e-05,
+      "loss": 0.9161809539794922,
+      "mean_token_accuracy": 0.7725442545861005,
+      "num_tokens": 5777733.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.0169112877128645,
+      "epoch": 0.7670018748934719,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 2.7363787916003037e-05,
+      "loss": 0.9725022888183594,
+      "mean_token_accuracy": 0.777765890210867,
+      "num_tokens": 5909211.0,
+      "step": 1125
+    },
+    {
+      "entropy": 0.9282390323840082,
+      "epoch": 0.7840463610022158,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 2.368032180614118e-05,
+      "loss": 0.8365528869628907,
+      "mean_token_accuracy": 0.7959657093882561,
+      "num_tokens": 6044115.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.9648981914808974,
+      "epoch": 0.8010908471109596,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 2.0229614809492303e-05,
+      "loss": 0.8802178955078125,
+      "mean_token_accuracy": 0.7891545896232128,
+      "num_tokens": 6175533.0,
+      "step": 1175
+    },
+    {
+      "entropy": 0.8922164059896022,
+      "epoch": 0.8181353332197034,
+      "grad_norm": 0.05859375,
+      "learning_rate": 1.7022190863257183e-05,
+      "loss": 0.8290106201171875,
+      "mean_token_accuracy": 0.8064813084155321,
+      "num_tokens": 6310296.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.9672217888385057,
+      "epoch": 0.8351798193284472,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 1.4067831942033904e-05,
+      "loss": 0.908281478881836,
+      "mean_token_accuracy": 0.7912823136150837,
+      "num_tokens": 6436503.0,
+      "step": 1225
+    },
+    {
+      "entropy": 1.0066828985884786,
+      "epoch": 0.8522243054371911,
+      "grad_norm": 0.06494140625,
+      "learning_rate": 1.137554822483381e-05,
+      "loss": 0.9817295074462891,
+      "mean_token_accuracy": 0.7799629791080952,
+      "num_tokens": 6572817.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.8913562398357316,
+      "epoch": 0.8692687915459348,
+      "grad_norm": 0.07421875,
+      "learning_rate": 8.953550615913397e-06,
+      "loss": 0.7918276977539063,
+      "mean_token_accuracy": 0.8021628592163325,
+      "num_tokens": 6701599.0,
+      "step": 1275
+    },
+    {
+      "entropy": 0.9468374169385061,
+      "epoch": 0.8863132776546787,
+      "grad_norm": 0.07958984375,
+      "learning_rate": 6.809225703227351e-06,
+      "loss": 0.8823848724365234,
+      "mean_token_accuracy": 0.7927402850985527,
+      "num_tokens": 6838746.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.9219346580654383,
+      "epoch": 0.9033577637634226,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 4.949113230874847e-06,
+      "loss": 0.8668992614746094,
+      "mean_token_accuracy": 0.797563666626811,
+      "num_tokens": 6971712.0,
+      "step": 1325
+    },
+    {
+      "entropy": 0.984245891966857,
+      "epoch": 0.9204022498721663,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 3.3788861542428553e-06,
+      "loss": 0.9503571319580079,
+      "mean_token_accuracy": 0.792408836260438,
+      "num_tokens": 7106279.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.913267534552142,
+      "epoch": 0.9374467359809102,
+      "grad_norm": 0.115234375,
+      "learning_rate": 2.1033333386744846e-06,
+      "loss": 0.8369984436035156,
+      "mean_token_accuracy": 0.803322741240263,
+      "num_tokens": 7238150.0,
+      "step": 1375
+    },
+    {
+      "entropy": 0.8992303860466927,
+      "epoch": 0.954491222089654,
+      "grad_norm": 0.064453125,
+      "learning_rate": 1.1263449544276938e-06,
+      "loss": 0.8289890289306641,
+      "mean_token_accuracy": 0.8079592730104923,
+      "num_tokens": 7374135.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.9052433096244932,
+      "epoch": 0.9715357081983979,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 4.5090061246676475e-07,
+      "loss": 0.7991035461425782,
+      "mean_token_accuracy": 0.7997805786132812,
+      "num_tokens": 7508742.0,
+      "step": 1425
+    },
+    {
+      "entropy": 0.9894003225583583,
+      "epoch": 0.9885801943071416,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 7.906027726981568e-08,
+      "loss": 0.9240727233886719,
+      "mean_token_accuracy": 0.786658907160163,
+      "num_tokens": 7649672.0,
+      "step": 1450
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1467,
+  "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": 3.3015596632508314e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1467/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc4c6c929872f6609871e917db76edda2422f46a78f2141949ced04b85bfae0
+size 5649

checkpoint-500/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoint-500/adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06721c2fb4160186ce083e9278cddbc244c7f60a9d4ee7388df624195755e770
+size 80792880

checkpoint-500/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-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84aabd0716823d3888c21eafc1875935c94cfe5c3a2f44608cfc87427847e1fc
+size 161810747

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05efcfe29e9807f5d160974c56b6343c99f71214e836d55d7f9b90e70eaeed5a
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f53d1b692311bdef454f3af4d3ee73e18ccd05572da38b773834e3dd52469d4
+size 1465

checkpoint-500/tokenizer.json

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

checkpoint-500/tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "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": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.34088972217487645,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 2.163015019595623,
+      "epoch": 0.01704448610874382,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 2.4524998474121094,
+      "mean_token_accuracy": 0.5153323707729578,
+      "num_tokens": 132137.0,
+      "step": 25
+    },
+    {
+      "entropy": 2.2185084584355352,
+      "epoch": 0.03408897221748764,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.000199996095299633,
+      "loss": 2.173491668701172,
+      "mean_token_accuracy": 0.5537562420964242,
+      "num_tokens": 261404.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.9352111649513244,
+      "epoch": 0.051133458326231465,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.0001997948280489004,
+      "loss": 1.8705439758300781,
+      "mean_token_accuracy": 0.5959619037806988,
+      "num_tokens": 396323.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.76205413736403,
+      "epoch": 0.06817794443497528,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 0.00019928920737019733,
+      "loss": 1.6511923217773437,
+      "mean_token_accuracy": 0.6337622724473476,
+      "num_tokens": 527358.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.4949746784381568,
+      "epoch": 0.08522243054371911,
+      "grad_norm": 0.0625,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 1.3673600769042968,
+      "mean_token_accuracy": 0.6848376739770174,
+      "num_tokens": 655447.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.4837670608237385,
+      "epoch": 0.10226691665246293,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001973719973913012,
+      "loss": 1.4141250610351563,
+      "mean_token_accuracy": 0.6836329951137304,
+      "num_tokens": 790490.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.3150090302992612,
+      "epoch": 0.11931140276120675,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019596625518199077,
+      "loss": 1.2282736968994141,
+      "mean_token_accuracy": 0.7172392677515745,
+      "num_tokens": 925069.0,
+      "step": 175
+    },
+    {
+      "entropy": 1.3966816508676856,
+      "epoch": 0.13635588886995056,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00019426783589406642,
+      "loss": 1.3173268127441407,
+      "mean_token_accuracy": 0.7017394271492958,
+      "num_tokens": 1052891.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.2435051177628338,
+      "epoch": 0.15340037497869438,
+      "grad_norm": 0.042236328125,
+      "learning_rate": 0.00019228191935240007,
+      "loss": 1.115916519165039,
+      "mean_token_accuracy": 0.7378023877739907,
+      "num_tokens": 1184065.0,
+      "step": 225
+    },
+    {
+      "entropy": 1.3924890440981834,
+      "epoch": 0.17044486108743823,
+      "grad_norm": 0.072265625,
+      "learning_rate": 0.00019001456218857208,
+      "loss": 1.288157958984375,
+      "mean_token_accuracy": 0.7004149560630322,
+      "num_tokens": 1313612.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.3593159637693315,
+      "epoch": 0.18748934719618204,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 0.00018747267936940722,
+      "loss": 1.2840399169921874,
+      "mean_token_accuracy": 0.7129683202505112,
+      "num_tokens": 1444287.0,
+      "step": 275
+    },
+    {
+      "entropy": 1.2371155321784317,
+      "epoch": 0.20453383330492586,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00018466402310776708,
+      "loss": 1.1687215423583985,
+      "mean_token_accuracy": 0.73335683144629,
+      "num_tokens": 1577307.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.2478438840154558,
+      "epoch": 0.22157831941366968,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00018159715921991612,
+      "loss": 1.20022216796875,
+      "mean_token_accuracy": 0.732666322439909,
+      "num_tokens": 1711348.0,
+      "step": 325
+    },
+    {
+      "entropy": 1.1931916671898215,
+      "epoch": 0.2386228055224135,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.00017828144100156754,
+      "loss": 1.082593002319336,
+      "mean_token_accuracy": 0.7456949570775032,
+      "num_tokens": 1842011.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.1265690931119026,
+      "epoch": 0.2556672916311573,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00017472698070228047,
+      "loss": 1.0630721282958984,
+      "mean_token_accuracy": 0.7553409574180842,
+      "num_tokens": 1976056.0,
+      "step": 375
+    },
+    {
+      "entropy": 1.1145534914545714,
+      "epoch": 0.27271177773990113,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 0.00017094461868520622,
+      "loss": 1.0225981903076171,
+      "mean_token_accuracy": 0.7580388783663511,
+      "num_tokens": 2109389.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.25198206695728,
+      "epoch": 0.28975626384864495,
+      "grad_norm": 0.048828125,
+      "learning_rate": 0.00016694589036623988,
+      "loss": 1.194885482788086,
+      "mean_token_accuracy": 0.7303700438886881,
+      "num_tokens": 2240117.0,
+      "step": 425
+    },
+    {
+      "entropy": 1.1865128787327557,
+      "epoch": 0.30680074995738876,
+      "grad_norm": 0.0556640625,
+      "learning_rate": 0.0001627429910334058,
+      "loss": 1.118544158935547,
+      "mean_token_accuracy": 0.7400260034948587,
+      "num_tokens": 2364080.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.274649427868426,
+      "epoch": 0.3238452360661326,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00015834873865377077,
+      "loss": 1.1928933715820313,
+      "mean_token_accuracy": 0.7288886807858944,
+      "num_tokens": 2497166.0,
+      "step": 475
+    },
+    {
+      "entropy": 1.1076703028334305,
+      "epoch": 0.34088972217487645,
+      "grad_norm": 0.0693359375,
+      "learning_rate": 0.00015377653478131556,
+      "loss": 1.0115528869628907,
+      "mean_token_accuracy": 0.7560868422687054,
+      "num_tokens": 2632559.0,
+      "step": 500
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1467,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1232059347325645e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc4c6c929872f6609871e917db76edda2422f46a78f2141949ced04b85bfae0
+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": "<|im_end|>",
+  "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": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fc4c6c929872f6609871e917db76edda2422f46a78f2141949ced04b85bfae0
+size 5649