Downloads · 30 days
4
9% of all-time downloads
pegasus-lora-legalease
etav22/pegasus-lora-legalease
pegasus-lora-legalease is a machine learning model from etav22. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
should probably proofread and complete it, then remove this comment. --
All-time downloads
45
Public
Parameters
570M
13.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.7 GB · 100%
At a glance
- Library
- peft
- Model type
- pegasus
- Access
- Public
- Created
- Mar 7, 2024
- Updated
- Apr 1, 2024
- SHA
- 6fa2085a
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
pegasus-lora-legalease
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: 1.0284
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: 0.0002
- 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
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.09 | 250 | 1.2117 |
| 2.535 | 0.18 | 500 | 1.1464 |
| 2.535 | 0.27 | 750 | 1.1167 |
| 1.1997 | 0.35 | 1000 | 1.1002 |
| 1.1997 | 0.44 | 1250 | 1.0886 |
| 1.1701 | 0.53 | 1500 | 1.0825 |
| 1.1701 | 0.62 | 1750 | 1.0725 |
| 1.1146 | 0.71 | 2000 | 1.0659 |
| 1.1146 | 0.8 | 2250 | 1.0594 |
| 1.1141 | 0.89 | 2500 | 1.0564 |
| 1.1141 | 0.98 | 2750 | 1.0507 |
| 1.126 | 1.06 | 3000 | 1.0464 |
| 1.126 | 1.15 | 3250 | 1.0449 |
| 1.0872 | 1.24 | 3500 | 1.0410 |
| 1.0872 | 1.33 | 3750 | 1.0389 |
| 1.0696 | 1.42 | 4000 | 1.0361 |
| 1.0696 | 1.51 | 4250 | 1.0338 |
| 1.0879 | 1.6 | 4500 | 1.0328 |
| 1.0879 | 1.68 | 4750 | 1.0310 |
| 1.0611 | 1.77 | 5000 | 1.0302 |
| 1.0611 | 1.86 | 5250 | 1.0288 |
| 1.0643 | 1.95 | 5500 | 1.0284 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Library
- peft
- Type
- pegasus
- Created
- Mar 7, 2024
- Updated
- Apr 1, 2024