asril-pegasus

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

• Loss: 1.0562

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: 4
• eval_batch_size: 4
• seed: 42
• 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

Training results

Training Loss	Epoch	Step	Validation Loss
4.4062	0.1046	1000	1.3928
1.5209	0.2092	2000	1.2535
1.3845	0.3138	3000	1.1791
1.3249	0.4184	4000	1.1339
1.275	0.5230	5000	1.1066
1.235	0.6275	6000	1.0857
1.2299	0.7321	7000	1.0743
1.2036	0.8367	8000	1.0645
1.2115	0.9413	9000	1.0579

Framework versions

• Transformers 4.40.1
• Pytorch 2.1.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1