xlmr-burmese-power – AI Model by annasus10 | AlphaNeural AI

You can deploy this model and start earning money today!

annasus10/
xlmr-burmese-power

like

0

text-classification

generated_from_trainer

FacebookAI/xlm-roberta-base

endpoints_compatible

Views

No views yet

xlmr-burmese-power

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.9327
Accuracy: 0.7424
Macro F1: 0.6051
Weighted F1: 0.7576

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: 16
eval_batch_size: 32
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: linear
lr_scheduler_warmup_steps: 150
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Macro F1	Weighted F1
1.3882	1.0	97	1.3608	0.6485	0.3583	0.6283
1.3251	2.0	194	1.2136	0.4939	0.348	0.526
1.1775	3.0	291	1.1041	0.7364	0.4422	0.6988
0.9520	4.0	388	0.8395	0.5667	0.5321	0.6144
0.8024	5.0	485	0.9577	0.6636	0.536	0.69
0.6479	6.0	582	0.8802	0.6667	0.5681	0.7
0.5405	7.0	679	0.9347	0.7667	0.6207	0.7756
0.4214	8.0	776	0.9327	0.7424	0.6051	0.7576

Framework versions

Transformers 5.0.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2