bart-model2-1309

This model is a fine-tuned version of theojolliffe/bart-paraphrase-v4-e1-feedback on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1465
• Rouge1: 60.8818
• Rouge2: 53.2203
• Rougel: 60.2427
• Rougelsum: 60.557
• Gen Len: 19.6498

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.914	1.0	867	0.1465	60.8818	53.2203	60.2427	60.557	19.6498

Framework versions

• Transformers 4.12.3
• Pytorch 1.9.0
• Datasets 1.18.0
• Tokenizers 0.10.3