argilla-news-model

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

• Loss: 1.6567
• Rouge1: 52.1956
• Rouge2: 27.1191
• Rougel: 47.4447
• Rougelsum: 47.4865

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: 5.6e-05
• train_batch_size: 6
• eval_batch_size: 6
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
2.0471	1.0	1532	1.6910	50.7422	26.3198	46.3759	46.3969
1.4617	2.0	3064	1.6369	52.3416	27.1892	47.7014	47.7618
1.0947	3.0	4596	1.6567	52.1956	27.1191	47.4447	47.4865

Framework versions

• Transformers 4.29.1
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3