OnAnOrange

qwen3.5-4b-lite-osworld-scalecua-cuagym-sft-ep3

README

License: apache-2.0

Training

Data: cua-lite/Lite.OSWorld + cua-lite/Lite.ScaleCUA + cua-lite/Lite.CUAGym
Exported SFT parquet rows: 10,934 (including 5,000 sampled Lite.ScaleCUA rows)
Training job: Slurm 1986549
Checkpoint: iter_1022, saved at the end of epoch 3 of a 3-epoch run
Hyperparameters: 8 H200 GPUs, TP=2, DP=4, MBS=1, global batch size=32, LR=5e-6
Fixed BSHD maximum sequence length: 18,432

This is a model-weight checkpoint. The training job did not save optimizer state, so this artifact is suitable for inference or weight initialization but not exact optimizer-state resumption.

Provenance

CUA-Lite source commit: 8d2205b146a9857ed508f55bb09ba60d8e524b0c
Base model: Qwen/Qwen3.5-4B

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

OnAnOrange

Model Tree

Base

Qwen/Qwen3.5-4B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality