You can deploy this model and start earning money today!

contemmcm/
9eae58eb012a3e0e8364ac0dc68c1c91

Name: 9eae58eb012a3e0e8364ac0dc68c1c91
Rating: 2.5 (8 reviews)

Views

No views yet

9eae58eb012a3e0e8364ac0dc68c1c91

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

More information needed

More information needed

More information needed

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 Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro	Rouge1	Rougel	Rougelsum
No log	0	0	1.6597	0	2.8557	0.2486	0.0796	0.2486	0.2486	0.2479
No log	1	178	1.5684	0.0078	4.4193	0.2401	0.0774	0.2401	0.2408	0.2393
No log	2	356	1.3655	0.0156	3.7364	0.4581	0.2584	0.4588	0.4581	0.4588
No log	3	534	1.0809	0.0312	5.1344	0.5774	0.4065	0.5767	0.5774	0.5774
No log	4	712	0.9625	0.0625	6.6563	0.6811	0.5257	0.6825	0.6818	0.6811
No log	5	890	0.8426	0.125	9.5374	0.6783	0.4790	0.6797	0.6790	0.6776
0.0621	6	1068	0.7416	0.25	12.9791	0.7422	0.5805	0.7429	0.7422	0.7422
0.6636	7	1246	0.6786	0.5	19.5382	0.7415	0.5731	0.7422	0.7415	0.7415
0.5788	8.0	1424	0.5958	1.0	34.2120	0.7472	0.7571	0.7472	0.7472	0.7479
0.4884	9.0	1602	0.6293	1.0	32.1574	0.7607	0.7752	0.7614	0.7607	0.7607
0.3886	10.0	1780	0.5989	1.0	32.2243	0.7706	0.8082	0.7713	0.7713	0.7706
0.3399	11.0	1958	1.0590	1.0	33.2385	0.6676	0.7139	0.6676	0.6676	0.6676
0.2799	12.0	2136	0.8224	1.0	32.0843	0.7585	0.7997	0.7585	0.7585	0.7592