qwen3-8b-belebele-lora-mal-mlym – AI Model by xummer | AlphaNeural AI

You can deploy this model and start earning money today!

xummer/
qwen3-8b-belebele-lora-mal-mlym

like

0

text-generation

Views

No views yet

belebele_mal_Mlym

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

Loss: 0.4019
Accuracy: 0.9074
Mcq Accuracy: 0.5111

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: 0.0002
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.1
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcq Accuracy
0.3571	1.0	40	0.3555	0.9022	0.3444
0.2472	2.0	80	0.2741	0.9111	0.5
0.1603	3.0	120	0.2844	0.9136	0.5222
0.0575	4.0	160	0.3735	0.9077	0.5111
0.0383	5.0	200	0.4019	0.9074	0.5111

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2