xlm-roberta-large-finetuned-panx-ko

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

• Loss: 0.1649
• F1: 0.8934

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: 5e-06
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	587	0.2583	0.7471
No log	2.0	1174	0.1759	0.8449
0.5424	3.0	1761	0.1655	0.8648
0.5424	4.0	2348	0.1499	0.8796
0.1482	5.0	2935	0.1463	0.8805
0.1482	6.0	3522	0.1467	0.8823
0.1013	7.0	4109	0.1560	0.8850
0.1013	8.0	4696	0.1529	0.8879
0.0768	9.0	5283	0.1598	0.8909
0.0768	10.0	5870	0.1585	0.8943
0.0604	11.0	6457	0.1629	0.8920
0.0604	12.0	7044	0.1649	0.8934

Framework versions

• Transformers 4.16.2
• Pytorch 2.6.0+cu124
• Datasets 1.16.1
• Tokenizers 0.21.2