BART_CNNDM_ORIGIN

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

• Loss: 1.6921
• Rouge1: 0.3423
• Rouge2: 0.144
• Rougel: 0.2434
• Rougelsum: 0.3142
• Gen Len: 73.4636
• Precision: 0.8695
• Recall: 0.8927
• F1: 0.8808

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: 8
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Precision	Recall	F1
1.2137	1.0	625	1.6451	0.3343	0.1359	0.2346	0.3043	72.7655	0.8678	0.891	0.8791
1.054	2.0	1250	1.6921	0.3423	0.144	0.2434	0.3142	73.4636	0.8695	0.8927	0.8808

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.15.0