2db6019289449a695dcc3dce40353968

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll03-german on the nyu-mll/glue [qnli] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6932
• Data Size: 1.0
• Epoch Runtime: 505.5655
• Accuracy: 0.5057
• F1 Macro: 0.3359
• Rouge1: 0.5053
• Rouge2: 0.0
• Rougel: 0.5057
• Rougelsum: 0.5056

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	Rouge1	Rouge2	Rougel	Rougelsum
No log	0	0	0.7048	0	8.1442	0.5064	0.3509	0.5064	0.0	0.5061	0.5064
No log	1	3273	0.6979	0.0078	12.4270	0.5193	0.4141	0.5189	0.0	0.5190	0.5193
0.0114	2	6546	0.6940	0.0156	17.0283	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.7073	3	9819	0.7107	0.0312	25.6120	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7017	4	13092	0.6941	0.0625	41.0203	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.7004	5	16365	0.6936	0.125	72.6893	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6987	6	19638	0.6925	0.25	133.7448	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6969	7	22911	0.7013	0.5	259.8177	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6944	8.0	26184	0.6932	1.0	507.4146	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.695	9.0	29457	0.6945	1.0	506.6142	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6956	10.0	32730	0.6921	1.0	505.3873	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.697	11.0	36003	0.6915	1.0	506.8079	0.4915	0.3452	0.4917	0.0	0.4919	0.4915
0.6976	12.0	39276	0.6947	1.0	505.7576	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6959	13.0	42549	0.6928	1.0	506.2805	0.5057	0.3359	0.5053	0.0	0.5057	0.5056
0.6958	14.0	45822	0.6937	1.0	504.0697	0.4943	0.3308	0.4947	0.0	0.4943	0.4944
0.6944	15.0	49095	0.6932	1.0	505.5655	0.5057	0.3359	0.5053	0.0	0.5057	0.5056

Framework versions

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