cu-go-bart-base-gc

This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5455
• Rouge1: 53.0097
• Rouge2: 29.8987
• Rougel: 37.7495
• Rougelsum: 49.1744
• Gen Len: 106.6047

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	86	1.6037	51.0086	27.7443	35.7708	47.0373	108.2442
No log	2.0	172	1.5580	53.4388	29.9039	37.6105	49.6511	109.1163
No log	3.0	258	1.5455	53.0097	29.8987	37.7495	49.1744	106.6047

Framework versions

• Transformers 4.35.0.dev0
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.14.1