akshay4/budget-router-sft-qwen1.5b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: akshay4/budget-router-sft-qwen1.5b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-16 03:43:16 +08:00
commit 7ec14ecd98
9 changed files with 1144 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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
tokenizer.json filter=lfs diff=lfs merge=lfs -text

201
README.md Normal file
View File

@@ -0,0 +1,201 @@
---
library_name: transformers
tags:
- trl
- sft
---
# 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. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **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]

54
chat_template.jinja Normal file
View File

@@ -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 %}

61
config.json Normal file
View File

@@ -0,0 +1,61 @@
{
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 1536,
"initializer_range": 0.02,
"intermediate_size": 8960,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 21,
"model_type": "qwen2",
"num_attention_heads": 12,
"num_hidden_layers": 28,
"num_key_value_heads": 2,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000.0,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.6.2",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

743
eval_results_sft.json Normal file
View File

@@ -0,0 +1,743 @@
{
"budget_guard": true,
"cohens_d": -0.4012815565141226,
"delta": -0.019029999999999984,
"episodes": [
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.6307,
"budget_score": 0.0727,
"latency_score": 0.4393,
"overall_score": 0.5549,
"sla_score": 0.9,
"success_score": 0.65
},
"grader_score": 0.5549,
"metrics": {
"average_latency_ms": 280.34,
"queue_overflow_events": 0,
"sla_met": false,
"success_rate": 0.65,
"total_cost_spent": 1.02,
"total_reward": -5.7566
},
"total_reward": -5.756610262130129
},
"seed": 300,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.5208,
"budget_score": 0.3182,
"latency_score": 0.4994,
"overall_score": 0.5368,
"sla_score": 1.0,
"success_score": 0.45
},
"grader_score": 0.5368,
"metrics": {
"average_latency_ms": 250.32,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.6,
"total_cost_spent": 0.75,
"total_reward": -8.9091
},
"parse_failures": 0,
"total_reward": -8.909090909090912
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.5852,
"budget_score": 0.1364,
"latency_score": 0.4182,
"overall_score": 0.5361,
"sla_score": 0.9,
"success_score": 0.6
},
"grader_score": 0.5361,
"metrics": {
"average_latency_ms": 290.91,
"queue_overflow_events": 0,
"sla_met": false,
"success_rate": 0.6,
"total_cost_spent": 0.95,
"total_reward": -8.4167
},
"total_reward": -8.41672666635194
},
"seed": 301,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.55,
"budget_score": 0.2727,
"latency_score": 0.5036,
"overall_score": 0.5516,
"sla_score": 1.0,
"success_score": 0.5
},
"grader_score": 0.5516,
"metrics": {
"average_latency_ms": 248.19,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.625,
"total_cost_spent": 0.8,
"total_reward": -7.6364
},
"parse_failures": 0,
"total_reward": -7.6363636363636385
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.7333,
"budget_score": 0.0364,
"latency_score": 0.5096,
"overall_score": 0.614,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.614,
"metrics": {
"average_latency_ms": 245.22,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7,
"total_cost_spent": 1.06,
"total_reward": -2.8182
},
"total_reward": -2.81818181818182
},
"seed": 302,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.6944,
"budget_score": 0.2727,
"latency_score": 0.5664,
"overall_score": 0.6081,
"sla_score": 1.0,
"success_score": 0.55
},
"grader_score": 0.6081,
"metrics": {
"average_latency_ms": 216.8,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.6875,
"total_cost_spent": 0.8,
"total_reward": -4.6364
},
"parse_failures": 0,
"total_reward": -4.636363636363638
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.7619,
"budget_score": 0.0364,
"latency_score": 0.5229,
"overall_score": 0.5836,
"sla_score": 0.9412,
"success_score": 0.6
},
"grader_score": 0.5836,
"metrics": {
"average_latency_ms": 238.56,
"queue_overflow_events": 0,
"sla_met": false,
"success_rate": 0.7059,
"total_cost_spent": 1.06,
"total_reward": -4.4089
},
"total_reward": -4.408894533537559
},
"seed": 303,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.4881,
"budget_score": 0.3636,
"latency_score": 0.3641,
"overall_score": 0.4543,
"sla_score": 0.9286,
"success_score": 0.3
},
"grader_score": 0.4543,
"metrics": {
"average_latency_ms": 317.95,
"queue_overflow_events": 0,
"sla_met": false,
"success_rate": 0.4286,
"total_cost_spent": 0.7,
"total_reward": -16.2086
},
"parse_failures": 0,
"total_reward": -16.208615567898335
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.6607,
"budget_score": 0.0818,
"latency_score": 0.5069,
"overall_score": 0.6058,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.6058,
"metrics": {
"average_latency_ms": 246.53,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7,
"total_cost_spent": 1.01,
"total_reward": -2.5909
},
"total_reward": -2.590909090909092
},
"seed": 304,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.6696,
"budget_score": 0.2727,
"latency_score": 0.536,
"overall_score": 0.597,
"sla_score": 1.0,
"success_score": 0.55
},
"grader_score": 0.597,
"metrics": {
"average_latency_ms": 232.01,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.6875,
"total_cost_spent": 0.8,
"total_reward": -4.6364
},
"parse_failures": 0,
"total_reward": -4.636363636363638
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.6333,
"budget_score": 0.1364,
"latency_score": 0.4553,
"overall_score": 0.5757,
"sla_score": 0.95,
"success_score": 0.65
},
"grader_score": 0.5757,
"metrics": {
"average_latency_ms": 272.37,
"queue_overflow_events": 0,
"sla_met": false,
"success_rate": 0.65,
"total_cost_spent": 0.95,
"total_reward": -5.3343
},
"total_reward": -5.3342661209730835
},
"seed": 305,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.5429,
"budget_score": 0.1818,
"latency_score": 0.4658,
"overall_score": 0.5357,
"sla_score": 0.9444,
"success_score": 0.55
},
"grader_score": 0.5357,
"metrics": {
"average_latency_ms": 267.08,
"queue_overflow_events": 1,
"sla_met": false,
"success_rate": 0.6111,
"total_cost_spent": 0.9,
"total_reward": -8.1537
},
"parse_failures": 0,
"total_reward": -8.153655932753445
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.7125,
"budget_score": 0.0636,
"latency_score": 0.5269,
"overall_score": 0.6174,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.6174,
"metrics": {
"average_latency_ms": 236.53,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7368,
"total_cost_spent": 1.03,
"total_reward": -1.1818
},
"total_reward": -1.1818181818181825
},
"seed": 306,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.5,
"budget_score": 0.2727,
"latency_score": 0.5516,
"overall_score": 0.5662,
"sla_score": 1.0,
"success_score": 0.55
},
"grader_score": 0.5662,
"metrics": {
"average_latency_ms": 224.18,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.6875,
"total_cost_spent": 0.8,
"total_reward": -4.6364
},
"parse_failures": 0,
"total_reward": -4.636363636363639
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.6667,
"budget_score": 0.1636,
"latency_score": 0.4865,
"overall_score": 0.6152,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.6152,
"metrics": {
"average_latency_ms": 256.73,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7,
"total_cost_spent": 0.92,
"total_reward": -2.1818
},
"total_reward": -2.1818181818181825
},
"seed": 307,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.75,
"budget_score": 0.2273,
"latency_score": 0.5844,
"overall_score": 0.661,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.661,
"metrics": {
"average_latency_ms": 207.79,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.8235,
"total_cost_spent": 0.85,
"total_reward": 2.6364
},
"parse_failures": 0,
"total_reward": 2.636363636363633
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.8,
"budget_score": 0.0818,
"latency_score": 0.53,
"overall_score": 0.6233,
"sla_score": 1.0,
"success_score": 0.65
},
"grader_score": 0.6233,
"metrics": {
"average_latency_ms": 234.98,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7222,
"total_cost_spent": 1.01,
"total_reward": -2.5909
},
"total_reward": -2.590909090909092
},
"seed": 308,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.7222,
"budget_score": 0.2273,
"latency_score": 0.536,
"overall_score": 0.6157,
"sla_score": 1.0,
"success_score": 0.6
},
"grader_score": 0.6157,
"metrics": {
"average_latency_ms": 232.02,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7059,
"total_cost_spent": 0.85,
"total_reward": -3.3636
},
"parse_failures": 0,
"total_reward": -3.363636363636367
}
},
{
"heuristic": {
"episode_length": 20,
"grader": {
"adaptation_score": 0.8333,
"budget_score": 0.0364,
"latency_score": 0.5286,
"overall_score": 0.6378,
"sla_score": 1.0,
"success_score": 0.7
},
"grader_score": 0.6378,
"metrics": {
"average_latency_ms": 235.72,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7778,
"total_cost_spent": 1.06,
"total_reward": 0.1818
},
"total_reward": 0.18181818181817988
},
"seed": 309,
"sft": {
"actions": [
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"route_to_b",
"route_to_b",
"shed_load",
"route_to_b",
"shed_load",
"route_to_b"
],
"episode_length": 20,
"grader": {
"adaptation_score": 0.75,
"budget_score": 0.2273,
"latency_score": 0.5901,
"overall_score": 0.6471,
"sla_score": 1.0,
"success_score": 0.65
},
"grader_score": 0.6471,
"metrics": {
"average_latency_ms": 204.93,
"queue_overflow_events": 0,
"sla_met": true,
"success_rate": 0.7647,
"total_cost_spent": 0.85,
"total_reward": -0.3636
},
"parse_failures": 0,
"total_reward": -0.36363636363636687
}
}
],
"heuristic_ci95": [
0.5730399213096795,
0.6197200786903205
],
"heuristic_scores": [
0.5549,
0.5361,
0.614,
0.5836,
0.6058,
0.5757,
0.6174,
0.6152,
0.6233,
0.6378
],
"losses": 7,
"mean_heuristic": 0.59638,
"mean_sft": 0.57735,
"n_seeds": 10,
"p_val": 0.8818559338559583,
"seeds": [
300,
301,
302,
303,
304,
305,
306,
307,
308,
309
],
"sft_ci95": [
0.5333993497309836,
0.6213006502690165
],
"sft_scores": [
0.5368,
0.5516,
0.6081,
0.4543,
0.597,
0.5357,
0.5662,
0.661,
0.6157,
0.6471
],
"significant": false,
"std_heuristic": 0.03262718021663669,
"std_sft": 0.061438772593353286,
"t_stat": -1.2689637016022048,
"task": "hard_multi",
"ties": 0,
"wins": 3
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.6.2"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bd808cf8448062cf9209ed706c235cbd0546c523be81ee8f4b535e270a7a9022
size 3087467144

3
tokenizer.json Normal file
View File

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

30
tokenizer_config.json Normal file
View File

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