donoway/ARC-Easy_Llama-3.2-1B-oqrx1b71

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Aug 19, 2025License:llama3.2Architecture:Transformer Warm

The donoway/ARC-Easy_Llama-3.2-1B-oqrx1b71 is a 1 billion parameter language model, fine-tuned from Meta's Llama-3.2-1B architecture. This model demonstrates an overall accuracy of 0.6509 on its evaluation set, with a generative accuracy of 0.5719. It is a compact model suitable for tasks where a smaller footprint and moderate accuracy are acceptable.

Loading preview...

Model Overview

The donoway/ARC-Easy_Llama-3.2-1B-oqrx1b71 is a 1 billion parameter language model, fine-tuned from the meta-llama/Llama-3.2-1B base model. It was trained for 100 epochs using a learning rate of 2e-05 and a batch size of 64.

Key Evaluation Metrics

During its evaluation, the model achieved the following results:

  • Overall Accuracy: 0.6509
  • Generative Accuracy: 0.5719
  • Loss: 3.7385

Specific accuracy metrics were also recorded for different label sets, with Accuracy 33 reaching 0.7434 and Gen Accuracy 33 at 0.7237.

Training Configuration

The training process utilized AdamW_Torch as the optimizer with a cosine learning rate scheduler and a warmup ratio of 0.01. The model was developed using Transformers 4.51.3, Pytorch 2.6.0+cu124, Datasets 3.5.0, and Tokenizers 0.21.1.

Potential Use Cases

Given its 1 billion parameters and observed accuracy, this model could be suitable for applications requiring a lightweight language model with moderate performance, such as:

  • Basic text generation
  • Simple classification tasks
  • Edge device deployment where computational resources are limited