AIPlans/qwen3-0.6b-base-hl-RM

Model Card for Model ID

A reward model to evaluate and score AI outputs.

Model Details

Model Description

This is the model card of Reward Model fine-tuned from Qwen3 model using the Anthropic's hh-rlhf dataset. The model is trained and evaluated on the harmless base subset of the Dataset.

• Developed by: AI PLans
• Model type: Reward Model
• Finetuned from model [Qwen3]: Qwen3-0.6b-base

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

Uses

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Recommendations

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

[More Information Needed]

Training Procedure

Preprocessing [optional]

[More Information Needed]

Training Hyperparameters

• Training regime: fp16,batch size=16,gradient_accumulation=32,epoch=2

Speeds, Sizes, Times [optional]

Testing Data

Anthropic-hh-rlhf Harmless base test data

Results

final epoch results

training loss	validation loss	Accuracy
0.5975	0.5518	0.7177

Model Examination [optional]

[More Information Needed]

• Hardware Type: GPU A100
• Hours used: ~2.5 hours