9df2bb8ec997569d492ecc7a19f37d0d

This model is a fine-tuned version of FacebookAI/xlm-roberta-large-finetuned-conll02-spanish on the nyu-mll/glue [mrpc] dataset. It achieves the following results on the evaluation set:

• Loss: 0.6429
• Data Size: 1.0
• Epoch Runtime: 24.2241
• Accuracy: 0.6651
• F1 Macro: 0.3994
• Rouge1: 0.6657
• Rouge2: 0.0
• Rougel: 0.6645
• Rougelsum: 0.6651

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	0.6429	0	2.9684	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	1	114	0.6521	0.0078	4.4424	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	2	228	0.6595	0.0156	4.1890	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
No log	3	342	0.6510	0.0312	5.1883	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0225	4	456	0.6409	0.0625	6.5716	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0225	5	570	0.6416	0.125	7.6501	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.0225	6	684	0.6930	0.25	11.4039	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.1636	7	798	0.6372	0.5	15.4502	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6487	8.0	912	0.6420	1.0	23.4243	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6472	9.0	1026	0.6366	1.0	22.9335	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6325	10.0	1140	0.6381	1.0	22.9975	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6493	11.0	1254	0.6388	1.0	22.6450	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6449	12.0	1368	0.6490	1.0	23.4097	0.6651	0.3994	0.6657	0.0	0.6645	0.6651
0.6473	13.0	1482	0.6429	1.0	24.2241	0.6651	0.3994	0.6657	0.0	0.6645	0.6651

Framework versions

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