bart-large-cnn-1000-lit-evalMA-NOpad

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

• Loss: 1.9804
• Rouge1: 27.2698
• Rouge2: 11.8561
• Rougel: 20.5948
• Rougelsum: 23.5497
• Gen Len: 67.67

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: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.5372	1.0	1000	1.7499	27.7275	12.7894	21.1334	24.4929	66.31
0.7344	2.0	2000	1.9804	27.2698	11.8561	20.5948	23.5497	67.67

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2
• Datasets 1.18.3
• Tokenizers 0.11.0