pegasus-text-simplification_1e4_adafactor_wikilarge_20epici

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

• Loss: 0.3934

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: 0.0001
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss
0.9542	1.0	803	0.3416
0.3111	2.0	1606	0.3372
0.2919	3.0	2409	0.3356
0.2659	4.0	3212	0.3389
0.2476	5.0	4015	0.3421
0.2351	6.0	4818	0.3474
0.2215	7.0	5621	0.3496
0.2141	8.0	6424	0.3548
0.2015	9.0	7227	0.3607
0.1921	10.0	8030	0.3628
0.1863	11.0	8833	0.3706
0.1794	12.0	9636	0.3734
0.1753	13.0	10439	0.3781
0.1697	14.0	11242	0.3814
0.1659	15.0	12045	0.3839
0.1626	16.0	12848	0.3878
0.1591	17.0	13651	0.3890
0.1575	18.0	14454	0.3921
0.1556	19.0	15257	0.3921
0.1545	20.0	16060	0.3934

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3