pegasus-newsroom-cnn_full-adafactor-bs6

This model is a fine-tuned version of oMateos2020/pegasus-newsroom-cnn_full-adafactor-bs6 on the cnn_dailymail dataset. It achieves the following results on the evaluation set:

• Loss: 2.8671
• Rouge1: 44.1026
• Rouge2: 21.4261
• Rougel: 31.2033
• Rougelsum: 41.0324
• Gen Len: 72.0839

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: 6.4e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 64
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 1
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.9343	0.5	560	2.8733	44.1226	21.4087	31.2431	41.0683	69.367
2.9855	1.0	1120	2.8671	44.1026	21.4261	31.2033	41.0324	72.0839

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu113
• Datasets 2.4.0
• Tokenizers 0.12.1