summary_naty_model

This model is a fine-tuned version of mrm8488/bart-legal-base-es on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.7235
• Rouge1: 0.2139
• Rouge2: 0.1064
• Rougel: 0.1798
• Rougelsum: 0.1802
• Gen Len: 20.0

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: 2e-05
• train_batch_size: 20
• eval_batch_size: 14
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 11
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	26	3.1779	0.2079	0.0817	0.1695	0.1697	20.0
No log	2.0	52	3.0521	0.2127	0.0875	0.1722	0.1725	20.0
No log	3.0	78	2.9548	0.2176	0.094	0.1742	0.1746	20.0
No log	4.0	104	2.8885	0.2191	0.0987	0.1761	0.1768	20.0
No log	5.0	130	2.8342	0.2176	0.1021	0.1767	0.177	20.0
No log	6.0	156	2.8070	0.2175	0.1042	0.1773	0.1776	20.0
No log	7.0	182	2.7686	0.2157	0.1044	0.1776	0.1781	20.0
No log	8.0	208	2.7491	0.2154	0.1038	0.1779	0.178	20.0
No log	9.0	234	2.7387	0.2133	0.1059	0.1771	0.1778	20.0
No log	10.0	260	2.7247	0.2131	0.1039	0.1781	0.1783	20.0
No log	11.0	286	2.7235	0.2139	0.1064	0.1798	0.1802	20.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0