e05359a46d292ddc932870d3dfb34355

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-german on the contemmcm/trec dataset. It achieves the following results on the evaluation set:

• Loss: 1.6687
• Data Size: 1.0
• Epoch Runtime: 32.0078
• Accuracy: 0.2771
• F1 Macro: 0.0723

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	1.8822	0	1.6032	0.1708	0.0769
No log	1	170	1.6967	0.0078	2.0759	0.2333	0.0798
No log	2	340	1.4667	0.0156	2.8822	0.3583	0.1832
No log	3	510	1.7586	0.0312	4.1685	0.3396	0.1777
No log	4	680	1.4077	0.0625	5.5279	0.4729	0.2781
0.1023	5	850	1.7724	0.125	8.4246	0.1417	0.0537
0.1023	6	1020	1.7079	0.25	11.6692	0.1792	0.0506
1.6695	7	1190	1.7281	0.5	19.1511	0.1792	0.0506
1.6719	8.0	1360	1.6687	1.0	32.0078	0.2771	0.0723

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1