Model Overview

This model, exp-syh-r2egym-swesmith-mixed_glm_4_7_traces_jupiter_cleaned, is an 8 billion parameter language model derived from the Qwen/Qwen3-8B architecture. It has been fine-tuned using a specific dataset located at /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-syh-r2egym-swesmith-mixed_glm_4.7_traces_jupiter_cleaned/snapshots/6bda9bf636a815d9ffd0a001e1a602b93c883472_thinking_preprocessed.

Training Details

The fine-tuning process involved several key hyperparameters:

• Learning Rate: 4e-05
• Batch Size: 1 (train), 8 (eval)
• Gradient Accumulation Steps: 2, leading to a total effective training batch size of 16 across 8 devices.
• Optimizer: ADAMW_TORCH_FUSED with betas=(0.9, 0.98) and epsilon=1e-08.
• LR Scheduler: Cosine type with a warmup ratio of 0.1.
• Epochs: 7.0

The training utilized Transformers 4.57.6, Pytorch 2.9.0+cu128, Datasets 4.4.1, and Tokenizers 0.22.2.

Intended Use Cases

Given its fine-tuning on a specific dataset, this model is likely suitable for tasks related to the domain or style of the training data. Users should evaluate its performance on their specific applications.