IndoT5-LoRA-R16-LR0.0003-Ep10 – AI Model by raniaa17 | AlphaNeural AI

You can deploy this model and start earning money today!

raniaa17/
IndoT5-LoRA-R16-LR0.0003-Ep10

like

0

Wikidepia/IndoT5-base

Views

No views yet

IndoT5-LoRA-R16-LR0.0003-Ep10

This model is a fine-tuned version of Wikidepia/IndoT5-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4506

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: 0.0003
train_batch_size: 64
eval_batch_size: 64
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: constant
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.8893	1.0	188	0.8337
0.5922	2.0	376	0.5895
0.5916	3.0	564	0.5424
0.527	4.0	752	0.5372
0.5916	5.0	940	0.5185
0.5307	6.0	1128	0.5174
0.5601	7.0	1316	0.5139
0.5165	8.0	1504	0.5066
0.4518	9.0	1692	0.4548
0.4349	10.0	1880	0.4506

Framework versions

PEFT 0.18.1
Transformers 4.57.6
Pytorch 2.10.0+cu128
Datasets 4.5.0
Tokenizers 0.22.2