pegasus-xsum / README.md
judy93536's picture
End of training
c3ecf04
|
raw
history blame
2.29 kB
metadata
base_model: google/pegasus-xsum
tags:
  - generated_from_trainer
model-index:
  - name: pegasus-xsum
    results: []

pegasus-xsum

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: 0.1676

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: 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: 8

Training results

Training Loss Epoch Step Validation Loss
2.2677 0.4 1000 0.1598
0.0619 0.8 2000 0.1363
0.0478 1.2 3000 0.1305
0.0421 1.6 4000 0.1298
0.0403 2.0 5000 0.1256
0.0328 2.4 6000 0.1309
0.0314 2.8 7000 0.1296
0.0294 3.2 8000 0.1381
0.0259 3.6 9000 0.1383
0.0251 4.0 10000 0.1380
0.0213 4.4 11000 0.1450
0.0206 4.8 12000 0.1427
0.0201 5.2 13000 0.1520
0.0189 5.6 14000 0.1505
0.0164 6.0 15000 0.1515
0.0153 6.4 16000 0.1594
0.0153 6.8 17000 0.1570
0.0149 7.2 18000 0.1652
0.0136 7.6 19000 0.1662
0.013 8.0 20000 0.1676

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.1