qwen3-8b-probe-better

tytodd/qwen3-8b-probe-better

qwen3-8b-probe-better is a machine learning model from tytodd. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

3% of all-time downloads

All-time downloads

149

Public

Repo size

134 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors61.4 MB · 84%

At a glance

Library: peft
License: apache-2.0
Access: Public
Created: Mar 2, 2026
Updated: Mar 3, 2026
SHA: 4b317076

Base models

Qwen/Qwen3-8B

Model card

From the Hugging Face model README

qwen3-8b-probe-better

This model is a fine-tuned version of Qwen/Qwen3-8B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0391

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 12
eval_batch_size: 12
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 6
total_train_batch_size: 576
total_eval_batch_size: 96
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.05
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.0449	0.4527	400	0.0457
0.0415	0.9053	800	0.0417
0.0400	1.3576	1200	0.0404
0.0389	1.8103	1600	0.0398
0.0382	2.2625	2000	0.0395
0.0376	2.7152	2400	0.0391

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.8.0+cu128
Datasets 4.6.1
Tokenizers 0.22.2

Library: peft
License: apache-2.0
Created: Mar 2, 2026
Updated: Mar 3, 2026