mluke-finetuned-tr – AI Model by zypchn | AlphaNeural AI

You can deploy this model and start earning money today!

zypchn/
mluke-finetuned-tr

like

0

generated_from_trainer

zypchn/rel-cls-tr

studio-ousia/mluke-base

endpoints_compatible

Views

No views yet

mluke-finetuned-tr

This model is a fine-tuned version of studio-ousia/mluke-base on zypchn/rel-cls-tr dataset. It achieves the following results on the evaluation set:

Loss: 0.2824
Accuracy: 0.9270
F1 Micro: 0.9270
F1 Macro: 0.9263

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: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Micro	F1 Macro
0.8959	1.0	164	0.3429	0.8904	0.8904	0.8844
0.2512	2.0	328	0.2707	0.9162	0.9162	0.9162
0.1439	3.0	492	0.2502	0.9280	0.9280	0.9272
0.0807	4.0	656	0.2737	0.9259	0.9259	0.9241
0.0502	5.0	820	0.2824	0.9270	0.9270	0.9263

Framework versions

Transformers 4.52.3
Pytorch 2.7.0+cu128
Datasets 3.6.0
Tokenizers 0.21.1