bart-paraphrase-v4-e1-feedback-e4

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: 1.9640
• Rouge1: 61.6305
• Rouge2: 41.9892
• Rougel: 57.0694
• Rougelsum: 58.3816
• Gen Len: 19.0

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: 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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	34	2.8512	67.5001	46.2823	62.2247	63.3811	18.875
No log	2.0	68	2.3116	62.1089	43.432	57.564	58.8003	19.0
No log	3.0	102	2.0519	61.2025	40.9901	56.3369	57.5829	19.0
No log	4.0	136	1.9640	61.6305	41.9892	57.0694	58.3816	19.0

Framework versions

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