c6c109a7e8e8bc0de2e9fda6d3ca5ac1

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-dutch on the contemmcm/amazon_reviews_2013 [cell-phone] dataset. It achieves the following results on the evaluation set:

• Loss: 1.5050
• Data Size: 0.5
• Epoch Runtime: 182.2522
• Accuracy: 0.3853
• F1 Macro: 0.1112

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-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	1.6562	0	22.1483	0.0973	0.0436
No log	1	1973	1.4889	0.0078	24.9047	0.3853	0.1112
0.0329	2	3946	1.4890	0.0156	27.3158	0.3853	0.1112
1.5031	3	5919	1.4841	0.0312	33.3895	0.3853	0.1112
1.4999	4	7892	1.4881	0.0625	44.0397	0.3853	0.1112
1.4782	5	9865	1.4902	0.125	64.0871	0.3853	0.1112
1.4962	6	11838	1.4949	0.25	102.6976	0.3853	0.1112
1.4983	7	13811	1.5050	0.5	182.2522	0.3853	0.1112

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.2.0
• Tokenizers 0.22.1