bart-large-cnn-finetuned-CNN-ML

This model is a fine-tuned version of facebook/bart-large-cnn on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 2.1137
• Rouge1: 44.4382
• Rouge2: 20.686
• Rougel: 29.9355
• Rougelsum: 41.4113
• Gen Len: 93.846

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.0341	1.0	1000	1.5412	43.0331	20.1656	29.6298	39.9858	83.22
0.6416	2.0	2000	1.8461	44.2294	20.5043	29.6298	41.1457	93.366
0.3766	3.0	3000	2.1137	44.4382	20.686	29.9355	41.4113	93.846

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3