sap_predictions_model

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: 6.3177
• Accuracy: 0.1599
• F1: 0.0713

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• 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
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
8.7072	0.6425	1000	8.5615	0.0156	0.0018
7.9463	1.2846	2000	7.8865	0.0445	0.0110
7.3576	1.9271	3000	7.2356	0.1019	0.0376
6.8566	2.5692	4000	6.7092	0.1424	0.0591
6.3983	3.2114	5000	6.3177	0.1599	0.0713
6.1392	3.8538	6000	6.0647	0.1756	0.0821
6.0378	4.4960	7000	5.9330	0.1819	0.0866

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1