Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ 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-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-50/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-Math-1.5B-Instruct
+library_name: peft
+model_name: verifier_v
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-Instruct
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for verifier_v
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B-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: 1.8.0
+- Transformers: 5.13.1
+- Pytorch: 2.11.0+cu128
+- Datasets: 5.0.0
+- 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 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-Math-1.5B-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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_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:cb5b41fb4b4e903baa332d87f01b54f9514adb7100dd7e11529e98474c5ccec4
+size 36981856

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- 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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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-100/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-100/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-Math-1.5B-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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_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-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1188548cba0fd319ee352e145a68df2179e8e74a1854e6a5632c010660e4bc0
+size 36981856

checkpoint-100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- 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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9a723bb5897b0bc2fb3bdbc41ac1e5ecf92585e833dc0c4132a027fd26c278e
+size 37974277

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b00cceb7f37cfbd31e90b394ecb76bb027606e7d08fb604a18f1196079d2df1
+size 14581

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a551ce0dc3a0b68845751a0c5e671b9aae2271abcf89a90290c712dcbcc1aa1f
+size 1465

checkpoint-100/tokenizer.json

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.111731843575419,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.478588992357254,
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0002,
+      "loss": 1.474172878265381,
+      "mean_token_accuracy": 0.7202531903982162,
+      "num_tokens": 139114.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0131698489189147,
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001992764570419069,
+      "loss": 0.890774917602539,
+      "mean_token_accuracy": 0.8060737997293472,
+      "num_tokens": 287784.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.7522242814302444,
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00019711629845587164,
+      "loss": 0.7361044406890869,
+      "mean_token_accuracy": 0.8316285818815231,
+      "num_tokens": 425110.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7530398115515708,
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001935507835925601,
+      "loss": 0.7272558689117432,
+      "mean_token_accuracy": 0.8267124712467193,
+      "num_tokens": 557368.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7576875060796737,
+      "epoch": 0.5586592178770949,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018863150851539877,
+      "loss": 0.7524267196655273,
+      "mean_token_accuracy": 0.8277575850486756,
+      "num_tokens": 697056.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_entropy": 0.736515037715435,
+      "eval_loss": 0.6621195673942566,
+      "eval_mean_token_accuracy": 0.8422216400504112,
+      "eval_num_tokens": 697056.0,
+      "eval_runtime": 2.5782,
+      "eval_samples_per_second": 24.824,
+      "eval_steps_per_second": 3.103,
+      "step": 50
+    },
+    {
+      "entropy": 0.6517506748437881,
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018242965936120768,
+      "loss": 0.6443954467773437,
+      "mean_token_accuracy": 0.8491255670785904,
+      "num_tokens": 839286.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.641720250248909,
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017503498221564025,
+      "loss": 0.6211273193359375,
+      "mean_token_accuracy": 0.8496817350387573,
+      "num_tokens": 975302.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6855695068836212,
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00016655448441021747,
+      "loss": 0.6648752689361572,
+      "mean_token_accuracy": 0.8399258822202682,
+      "num_tokens": 1124078.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6849436461925507,
+      "epoch": 1.0,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00015711088603430405,
+      "loss": 0.6506993293762207,
+      "mean_token_accuracy": 0.840119763424522,
+      "num_tokens": 1253938.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.5641703501343727,
+      "epoch": 1.111731843575419,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.5259711742401123,
+      "mean_token_accuracy": 0.8674439579248429,
+      "num_tokens": 1393724.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.111731843575419,
+      "eval_entropy": 0.5666306093335152,
+      "eval_loss": 0.614386796951294,
+      "eval_mean_token_accuracy": 0.8506837338209152,
+      "eval_num_tokens": 1393724.0,
+      "eval_runtime": 2.5795,
+      "eval_samples_per_second": 24.811,
+      "eval_steps_per_second": 3.101,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9212723876870144e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-150/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-150/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-Math-1.5B-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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_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-150/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84e70c6e381c46f35da7009bd4cd0211eca2135c5d25953aa99f22f660fcb5d5
+size 36981856

checkpoint-150/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- 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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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-150/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf51f874b2364fa4db8e5abfb6525b14941231bf73d5d3eb99af0e4b96dd18aa
+size 37974277

checkpoint-150/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c11bdc5c6e1b845f45ad1fbdf09cac78f999e50ad5181fa72b766ea960750c26
+size 14581

checkpoint-150/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e19896fb58eef00bd390945e94640b4e8b04179abcde093c2b43c5f0a52a26
+size 1465

checkpoint-150/tokenizer.json

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

checkpoint-150/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-150/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.670391061452514,
+  "eval_steps": 50,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.478588992357254,
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0002,
+      "loss": 1.474172878265381,
+      "mean_token_accuracy": 0.7202531903982162,
+      "num_tokens": 139114.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0131698489189147,
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001992764570419069,
+      "loss": 0.890774917602539,
+      "mean_token_accuracy": 0.8060737997293472,
+      "num_tokens": 287784.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.7522242814302444,
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00019711629845587164,
+      "loss": 0.7361044406890869,
+      "mean_token_accuracy": 0.8316285818815231,
+      "num_tokens": 425110.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7530398115515708,
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001935507835925601,
+      "loss": 0.7272558689117432,
+      "mean_token_accuracy": 0.8267124712467193,
+      "num_tokens": 557368.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7576875060796737,
+      "epoch": 0.5586592178770949,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018863150851539877,
+      "loss": 0.7524267196655273,
+      "mean_token_accuracy": 0.8277575850486756,
+      "num_tokens": 697056.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_entropy": 0.736515037715435,
+      "eval_loss": 0.6621195673942566,
+      "eval_mean_token_accuracy": 0.8422216400504112,
+      "eval_num_tokens": 697056.0,
+      "eval_runtime": 2.5782,
+      "eval_samples_per_second": 24.824,
+      "eval_steps_per_second": 3.103,
+      "step": 50
+    },
+    {
+      "entropy": 0.6517506748437881,
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018242965936120768,
+      "loss": 0.6443954467773437,
+      "mean_token_accuracy": 0.8491255670785904,
+      "num_tokens": 839286.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.641720250248909,
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017503498221564025,
+      "loss": 0.6211273193359375,
+      "mean_token_accuracy": 0.8496817350387573,
+      "num_tokens": 975302.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6855695068836212,
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00016655448441021747,
+      "loss": 0.6648752689361572,
+      "mean_token_accuracy": 0.8399258822202682,
+      "num_tokens": 1124078.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6849436461925507,
+      "epoch": 1.0,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00015711088603430405,
+      "loss": 0.6506993293762207,
+      "mean_token_accuracy": 0.840119763424522,
+      "num_tokens": 1253938.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.5641703501343727,
+      "epoch": 1.111731843575419,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.5259711742401123,
+      "mean_token_accuracy": 0.8674439579248429,
+      "num_tokens": 1393724.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.111731843575419,
+      "eval_entropy": 0.5666306093335152,
+      "eval_loss": 0.614386796951294,
+      "eval_mean_token_accuracy": 0.8506837338209152,
+      "eval_num_tokens": 1393724.0,
+      "eval_runtime": 2.5795,
+      "eval_samples_per_second": 24.811,
+      "eval_steps_per_second": 3.101,
+      "step": 100
+    },
+    {
+      "entropy": 0.6176844730973243,
+      "epoch": 1.223463687150838,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0001358929748480946,
+      "loss": 0.5868302822113037,
+      "mean_token_accuracy": 0.8550125420093536,
+      "num_tokens": 1532534.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6438683062791825,
+      "epoch": 1.3351955307262569,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00012442570344228313,
+      "loss": 0.6029658794403077,
+      "mean_token_accuracy": 0.8529511451721191,
+      "num_tokens": 1672541.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6293192014098168,
+      "epoch": 1.446927374301676,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00011260497112202895,
+      "loss": 0.5964456558227539,
+      "mean_token_accuracy": 0.8509853184223175,
+      "num_tokens": 1814087.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6304957449436188,
+      "epoch": 1.558659217877095,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.00010060183403992856,
+      "loss": 0.5848664283752442,
+      "mean_token_accuracy": 0.8556152552366256,
+      "num_tokens": 1955877.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.5609178155660629,
+      "epoch": 1.670391061452514,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.858998790219753e-05,
+      "loss": 0.5216239929199219,
+      "mean_token_accuracy": 0.8666022419929504,
+      "num_tokens": 2094363.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.670391061452514,
+      "eval_entropy": 0.587046142667532,
+      "eval_loss": 0.592239260673523,
+      "eval_mean_token_accuracy": 0.8515560328960419,
+      "eval_num_tokens": 2094363.0,
+      "eval_runtime": 2.5806,
+      "eval_samples_per_second": 24.801,
+      "eval_steps_per_second": 3.1,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.903219164867584e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-200/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-200/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-Math-1.5B-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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_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-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad2159d27f804806cbf26017ca94745119d575fae0cf60f0a4649821f568ec0
+size 36981856

checkpoint-200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- 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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70f064df4d943fed6b81b43e66d3b484a4fada94b7305cc4e470827b3e5f8d60
+size 37974277

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c392f3b9eace95313e0d4de762d86ba3677ad2afa1ae84d28e5ee3a1c19411
+size 14581

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a55a546c33e1e182a81736782960db014dc560c492f4a21bcd1c8a4d650c4f
+size 1465

checkpoint-200/tokenizer.json

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,278 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.223463687150838,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.478588992357254,
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0002,
+      "loss": 1.474172878265381,
+      "mean_token_accuracy": 0.7202531903982162,
+      "num_tokens": 139114.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0131698489189147,
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001992764570419069,
+      "loss": 0.890774917602539,
+      "mean_token_accuracy": 0.8060737997293472,
+      "num_tokens": 287784.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.7522242814302444,
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00019711629845587164,
+      "loss": 0.7361044406890869,
+      "mean_token_accuracy": 0.8316285818815231,
+      "num_tokens": 425110.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7530398115515708,
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001935507835925601,
+      "loss": 0.7272558689117432,
+      "mean_token_accuracy": 0.8267124712467193,
+      "num_tokens": 557368.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7576875060796737,
+      "epoch": 0.5586592178770949,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018863150851539877,
+      "loss": 0.7524267196655273,
+      "mean_token_accuracy": 0.8277575850486756,
+      "num_tokens": 697056.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_entropy": 0.736515037715435,
+      "eval_loss": 0.6621195673942566,
+      "eval_mean_token_accuracy": 0.8422216400504112,
+      "eval_num_tokens": 697056.0,
+      "eval_runtime": 2.5782,
+      "eval_samples_per_second": 24.824,
+      "eval_steps_per_second": 3.103,
+      "step": 50
+    },
+    {
+      "entropy": 0.6517506748437881,
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018242965936120768,
+      "loss": 0.6443954467773437,
+      "mean_token_accuracy": 0.8491255670785904,
+      "num_tokens": 839286.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.641720250248909,
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017503498221564025,
+      "loss": 0.6211273193359375,
+      "mean_token_accuracy": 0.8496817350387573,
+      "num_tokens": 975302.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6855695068836212,
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00016655448441021747,
+      "loss": 0.6648752689361572,
+      "mean_token_accuracy": 0.8399258822202682,
+      "num_tokens": 1124078.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6849436461925507,
+      "epoch": 1.0,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00015711088603430405,
+      "loss": 0.6506993293762207,
+      "mean_token_accuracy": 0.840119763424522,
+      "num_tokens": 1253938.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.5641703501343727,
+      "epoch": 1.111731843575419,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.5259711742401123,
+      "mean_token_accuracy": 0.8674439579248429,
+      "num_tokens": 1393724.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.111731843575419,
+      "eval_entropy": 0.5666306093335152,
+      "eval_loss": 0.614386796951294,
+      "eval_mean_token_accuracy": 0.8506837338209152,
+      "eval_num_tokens": 1393724.0,
+      "eval_runtime": 2.5795,
+      "eval_samples_per_second": 24.811,
+      "eval_steps_per_second": 3.101,
+      "step": 100
+    },
+    {
+      "entropy": 0.6176844730973243,
+      "epoch": 1.223463687150838,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0001358929748480946,
+      "loss": 0.5868302822113037,
+      "mean_token_accuracy": 0.8550125420093536,
+      "num_tokens": 1532534.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6438683062791825,
+      "epoch": 1.3351955307262569,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00012442570344228313,
+      "loss": 0.6029658794403077,
+      "mean_token_accuracy": 0.8529511451721191,
+      "num_tokens": 1672541.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6293192014098168,
+      "epoch": 1.446927374301676,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00011260497112202895,
+      "loss": 0.5964456558227539,
+      "mean_token_accuracy": 0.8509853184223175,
+      "num_tokens": 1814087.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6304957449436188,
+      "epoch": 1.558659217877095,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.00010060183403992856,
+      "loss": 0.5848664283752442,
+      "mean_token_accuracy": 0.8556152552366256,
+      "num_tokens": 1955877.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.5609178155660629,
+      "epoch": 1.670391061452514,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.858998790219753e-05,
+      "loss": 0.5216239929199219,
+      "mean_token_accuracy": 0.8666022419929504,
+      "num_tokens": 2094363.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.670391061452514,
+      "eval_entropy": 0.587046142667532,
+      "eval_loss": 0.592239260673523,
+      "eval_mean_token_accuracy": 0.8515560328960419,
+      "eval_num_tokens": 2094363.0,
+      "eval_runtime": 2.5806,
+      "eval_samples_per_second": 24.801,
+      "eval_steps_per_second": 3.1,
+      "step": 150
+    },
+    {
+      "entropy": 0.5698843523859978,
+      "epoch": 1.7821229050279328,
+      "grad_norm": 0.38671875,
+      "learning_rate": 7.674325444256899e-05,
+      "loss": 0.5345166206359864,
+      "mean_token_accuracy": 0.8647939324378967,
+      "num_tokens": 2229344.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5258378967642784,
+      "epoch": 1.893854748603352,
+      "grad_norm": 0.375,
+      "learning_rate": 6.523306607246527e-05,
+      "loss": 0.4891225814819336,
+      "mean_token_accuracy": 0.874450346827507,
+      "num_tokens": 2376372.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.59598287783171,
+      "epoch": 2.0,
+      "grad_norm": 0.57421875,
+      "learning_rate": 5.422598510671666e-05,
+      "loss": 0.5512537479400634,
+      "mean_token_accuracy": 0.859009651761306,
+      "num_tokens": 2507876.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5830112114548683,
+      "epoch": 2.111731843575419,
+      "grad_norm": 0.37890625,
+      "learning_rate": 4.388129346376178e-05,
+      "loss": 0.5075423240661621,
+      "mean_token_accuracy": 0.8701719880104065,
+      "num_tokens": 2647895.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5168617889285088,
+      "epoch": 2.223463687150838,
+      "grad_norm": 0.310546875,
+      "learning_rate": 3.4348687719438665e-05,
+      "loss": 0.45911827087402346,
+      "mean_token_accuracy": 0.8807366818189621,
+      "num_tokens": 2802239.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.223463687150838,
+      "eval_entropy": 0.5364116802811623,
+      "eval_loss": 0.5925846695899963,
+      "eval_mean_token_accuracy": 0.8547068387269974,
+      "eval_num_tokens": 2802239.0,
+      "eval_runtime": 2.5771,
+      "eval_samples_per_second": 24.834,
+      "eval_steps_per_second": 3.104,
+      "step": 200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.876419745063322e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-250/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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-250/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-Math-1.5B-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": [
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "v_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-250/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dccc3e0762cbd96e49c3c27013487ea1cfe487531596efc50e0a40774266fe7
+size 36981856

checkpoint-250/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'Please reason step by step, and put your final answer within \\boxed{}.' }}
+    {%- 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\nPlease reason step by step, and put your final answer within \\boxed{}.<|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-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d7d04815c0c840b1a65d80d871d320b8a116c1ce3f4dae087a36e4a0eef79d
+size 37974277

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8b16d1eab7608be89da36f22e1be37cf13ddb0e76c8a1172dfb26e8ce4f474b
+size 14581

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0584d6b91b7b9af26a855497dd39eb9f602459a7a1a8f40dc4214973e0d708b
+size 1465

checkpoint-250/tokenizer.json

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

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|fim_pad|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,339 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.782122905027933,
+  "eval_steps": 50,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.478588992357254,
+      "epoch": 0.11173184357541899,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0002,
+      "loss": 1.474172878265381,
+      "mean_token_accuracy": 0.7202531903982162,
+      "num_tokens": 139114.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.0131698489189147,
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.28515625,
+      "learning_rate": 0.0001992764570419069,
+      "loss": 0.890774917602539,
+      "mean_token_accuracy": 0.8060737997293472,
+      "num_tokens": 287784.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.7522242814302444,
+      "epoch": 0.33519553072625696,
+      "grad_norm": 0.3203125,
+      "learning_rate": 0.00019711629845587164,
+      "loss": 0.7361044406890869,
+      "mean_token_accuracy": 0.8316285818815231,
+      "num_tokens": 425110.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7530398115515708,
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.306640625,
+      "learning_rate": 0.0001935507835925601,
+      "loss": 0.7272558689117432,
+      "mean_token_accuracy": 0.8267124712467193,
+      "num_tokens": 557368.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7576875060796737,
+      "epoch": 0.5586592178770949,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018863150851539877,
+      "loss": 0.7524267196655273,
+      "mean_token_accuracy": 0.8277575850486756,
+      "num_tokens": 697056.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.5586592178770949,
+      "eval_entropy": 0.736515037715435,
+      "eval_loss": 0.6621195673942566,
+      "eval_mean_token_accuracy": 0.8422216400504112,
+      "eval_num_tokens": 697056.0,
+      "eval_runtime": 2.5782,
+      "eval_samples_per_second": 24.824,
+      "eval_steps_per_second": 3.103,
+      "step": 50
+    },
+    {
+      "entropy": 0.6517506748437881,
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00018242965936120768,
+      "loss": 0.6443954467773437,
+      "mean_token_accuracy": 0.8491255670785904,
+      "num_tokens": 839286.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.641720250248909,
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017503498221564025,
+      "loss": 0.6211273193359375,
+      "mean_token_accuracy": 0.8496817350387573,
+      "num_tokens": 975302.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6855695068836212,
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.00016655448441021747,
+      "loss": 0.6648752689361572,
+      "mean_token_accuracy": 0.8399258822202682,
+      "num_tokens": 1124078.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6849436461925507,
+      "epoch": 1.0,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00015711088603430405,
+      "loss": 0.6506993293762207,
+      "mean_token_accuracy": 0.840119763424522,
+      "num_tokens": 1253938.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.5641703501343727,
+      "epoch": 1.111731843575419,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00014684084406997903,
+      "loss": 0.5259711742401123,
+      "mean_token_accuracy": 0.8674439579248429,
+      "num_tokens": 1393724.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.111731843575419,
+      "eval_entropy": 0.5666306093335152,
+      "eval_loss": 0.614386796951294,
+      "eval_mean_token_accuracy": 0.8506837338209152,
+      "eval_num_tokens": 1393724.0,
+      "eval_runtime": 2.5795,
+      "eval_samples_per_second": 24.811,
+      "eval_steps_per_second": 3.101,
+      "step": 100
+    },
+    {
+      "entropy": 0.6176844730973243,
+      "epoch": 1.223463687150838,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.0001358929748480946,
+      "loss": 0.5868302822113037,
+      "mean_token_accuracy": 0.8550125420093536,
+      "num_tokens": 1532534.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6438683062791825,
+      "epoch": 1.3351955307262569,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00012442570344228313,
+      "loss": 0.6029658794403077,
+      "mean_token_accuracy": 0.8529511451721191,
+      "num_tokens": 1672541.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6293192014098168,
+      "epoch": 1.446927374301676,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00011260497112202895,
+      "loss": 0.5964456558227539,
+      "mean_token_accuracy": 0.8509853184223175,
+      "num_tokens": 1814087.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.6304957449436188,
+      "epoch": 1.558659217877095,
+      "grad_norm": 0.328125,
+      "learning_rate": 0.00010060183403992856,
+      "loss": 0.5848664283752442,
+      "mean_token_accuracy": 0.8556152552366256,
+      "num_tokens": 1955877.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.5609178155660629,
+      "epoch": 1.670391061452514,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.858998790219753e-05,
+      "loss": 0.5216239929199219,
+      "mean_token_accuracy": 0.8666022419929504,
+      "num_tokens": 2094363.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.670391061452514,
+      "eval_entropy": 0.587046142667532,
+      "eval_loss": 0.592239260673523,
+      "eval_mean_token_accuracy": 0.8515560328960419,
+      "eval_num_tokens": 2094363.0,
+      "eval_runtime": 2.5806,
+      "eval_samples_per_second": 24.801,
+      "eval_steps_per_second": 3.1,
+      "step": 150
+    },
+    {
+      "entropy": 0.5698843523859978,
+      "epoch": 1.7821229050279328,
+      "grad_norm": 0.38671875,
+      "learning_rate": 7.674325444256899e-05,
+      "loss": 0.5345166206359864,
+      "mean_token_accuracy": 0.8647939324378967,
+      "num_tokens": 2229344.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5258378967642784,
+      "epoch": 1.893854748603352,
+      "grad_norm": 0.375,
+      "learning_rate": 6.523306607246527e-05,
+      "loss": 0.4891225814819336,
+      "mean_token_accuracy": 0.874450346827507,
+      "num_tokens": 2376372.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.59598287783171,
+      "epoch": 2.0,
+      "grad_norm": 0.57421875,
+      "learning_rate": 5.422598510671666e-05,
+      "loss": 0.5512537479400634,
+      "mean_token_accuracy": 0.859009651761306,
+      "num_tokens": 2507876.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5830112114548683,
+      "epoch": 2.111731843575419,
+      "grad_norm": 0.37890625,
+      "learning_rate": 4.388129346376178e-05,
+      "loss": 0.5075423240661621,
+      "mean_token_accuracy": 0.8701719880104065,
+      "num_tokens": 2647895.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5168617889285088,
+      "epoch": 2.223463687150838,
+      "grad_norm": 0.310546875,
+      "learning_rate": 3.4348687719438665e-05,
+      "loss": 0.45911827087402346,
+      "mean_token_accuracy": 0.8807366818189621,
+      "num_tokens": 2802239.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.223463687150838,
+      "eval_entropy": 0.5364116802811623,
+      "eval_loss": 0.5925846695899963,
+      "eval_mean_token_accuracy": 0.8547068387269974,
+      "eval_num_tokens": 2802239.0,
+      "eval_runtime": 2.5771,
+      "eval_samples_per_second": 24.834,
+      "eval_steps_per_second": 3.104,
+      "step": 200
+    },
+    {
+      "entropy": 0.5113214284181595,
+      "epoch": 2.335195530726257,
+      "grad_norm": 0.353515625,
+      "learning_rate": 2.576611286891901e-05,
+      "loss": 0.4719066143035889,
+      "mean_token_accuracy": 0.8800413757562637,
+      "num_tokens": 2945305.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5378207266330719,
+      "epoch": 2.446927374301676,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.825776614411082e-05,
+      "loss": 0.4859320163726807,
+      "mean_token_accuracy": 0.87210513651371,
+      "num_tokens": 3079330.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5200178176164627,
+      "epoch": 2.558659217877095,
+      "grad_norm": 0.40234375,
+      "learning_rate": 1.1932299773007228e-05,
+      "loss": 0.4754458427429199,
+      "mean_token_accuracy": 0.878101596236229,
+      "num_tokens": 3218477.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.552644495666027,
+      "epoch": 2.6703910614525137,
+      "grad_norm": 0.435546875,
+      "learning_rate": 6.881248688597553e-06,
+      "loss": 0.5131622314453125,
+      "mean_token_accuracy": 0.870024585723877,
+      "num_tokens": 3364372.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.5456413477659225,
+      "epoch": 2.782122905027933,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.1777059397436692e-06,
+      "loss": 0.4786043643951416,
+      "mean_token_accuracy": 0.8750896036624909,
+      "num_tokens": 3501064.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.782122905027933,
+      "eval_entropy": 0.5384999848902225,
+      "eval_loss": 0.5904061198234558,
+      "eval_mean_token_accuracy": 0.8527737036347389,
+      "eval_num_tokens": 3501064.0,
+      "eval_runtime": 2.5743,
+      "eval_samples_per_second": 24.861,
+      "eval_steps_per_second": 3.108,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.8446915203584e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3f0e55ef6f28af070d9ef917c7e02ff815b9b702bccb82471082d69e77b490b
+size 5713

checkpoint-270/README.md

@@ -0,0 +1,209 @@
+---
+base_model: Qwen/Qwen2.5-Math-1.5B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-Math-1.5B-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