Qwen3-8B-QA – AI Model by Bagsangbin | AlphaNeural AI

You can deploy this model and start earning money today!

Bagsangbin/
Qwen3-8B-QA

like

0

text-generation

generated_from_trainer

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Qwen3-8B-QA

This model is a fine-tuned version of Qwen/Qwen3-8B on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8702
Accuracy: 0.0007

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: 2e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	39	0.8670	0.0007
1.2237	2.0	78	0.6869	0.0008
0.4504	3.0	117	0.7132	0.0008
0.1753	4.0	156	0.7544	0.0008
0.1753	5.0	195	0.7910	0.0007
0.0849	6.0	234	0.8127	0.0007
0.0583	7.0	273	0.8425	0.0007
0.0489	8.0	312	0.8606	0.0007
0.0451	9.0	351	0.8681	0.0007
0.0451	10.0	390	0.8702	0.0007

Framework versions

Transformers 4.53.2
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.2