bart-base-finetuned-kaggglenews-baseline-final

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: 1.6942
• Rouge1: 28.581
• Rouge2: 16.3417
• Rougel: 24.1277
• Rougelsum: 25.9797
• 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: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• 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	Gen Len
No log	1.0	495	1.7514	27.911	15.7038	23.6466	25.2111	20.0
2.0585	2.0	990	1.6655	28.7581	16.4875	24.2669	26.1676	20.0
1.4173	3.0	1485	1.6942	28.581	16.3417	24.1277	25.9797	20.0

Framework versions

• Transformers 4.12.5
• Pytorch 1.10.0+cu102
• Datasets 1.16.1
• Tokenizers 0.10.3