pegasus-finetuned-xsum-apollo_adamw

This model is a fine-tuned version of google/pegasus-xsum on the xsum dataset. It achieves the following results on the evaluation set:

• Loss: 1.4505
• Rouge1: 0.4893
• Rouge2: 0.2554
• Rougel: 0.4072
• Rougelsum: 0.4076
• Gen Len: 33.5333

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: 5e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Use OptimizerNames.APOLLO_ADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=proj=random,rank=1,scale=128.0,scale_type=tensor,update_proj_gap=300
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.0768	1.0	1200	1.4457	0.4853	0.253	0.4035	0.4042	34.4167
1.0271	2.0	2400	1.4505	0.4893	0.2554	0.4072	0.4076	33.5333
1.0061	3.0	3600	1.4547	0.4861	0.2519	0.405	0.4055	33.8833

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.2