Downloads · 30 days
5
17% of all-time downloads
ALLPrincipalPegasusLargeModel
MarPla/ALLPrincipalPegasusLargeModel
ALLPrincipalPegasusLargeModel is a machine learning model from MarPla. 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 transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
29
Public
Parameters
571M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 100%
At a glance
- Library
- transformers
- Model type
- pegasus
- Access
- Public
- Created
- Jun 9, 2024
- Updated
- Jun 9, 2024
- SHA
- fee4f5c8
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. -->
ALLPrincipalPegasusLargeModel
This model is a fine-tuned version of google/pegasus-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.0232
- Rouge1: 47.6658
- Rouge2: 14.3424
- Rougel: 32.0036
- Rougelsum: 44.3129
- Bertscore Precision: 80.0039
- Bertscore Recall: 82.2832
- Bertscore F1: 81.1232
- Bleu: 0.0968
- Gen Len: 215.5775
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bertscore Precision | Bertscore Recall | Bertscore F1 | Bleu | Gen Len |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 6.0475 | 0.1059 | 500 | 5.8195 | 40.9165 | 11.2781 | 27.4543 | 38.2464 | 77.6812 | 80.818 | 79.2126 | 0.0750 | 215.5775 |
| 5.7557 | 0.2118 | 1000 | 5.5171 | 44.1505 | 12.4929 | 29.115 | 41.1231 | 78.4631 | 81.3235 | 79.8626 | 0.0826 | 215.5775 |
| 5.5723 | 0.3178 | 1500 | 5.3613 | 45.368 | 13.0491 | 30.0119 | 42.2834 | 79.0906 | 81.6243 | 80.3329 | 0.0866 | 215.5775 |
| 5.5134 | 0.4237 | 2000 | 5.2571 | 45.8933 | 13.254 | 30.5132 | 42.7279 | 79.3615 | 81.82 | 80.5674 | 0.0886 | 215.5775 |
| 5.3793 | 0.5296 | 2500 | 5.1767 | 46.8804 | 13.7974 | 31.0723 | 43.5411 | 79.5774 | 82.0228 | 80.7769 | 0.0926 | 215.5775 |
| 5.4004 | 0.6355 | 3000 | 5.1101 | 46.7592 | 13.9082 | 31.3732 | 43.5105 | 79.7564 | 82.1032 | 80.9084 | 0.0934 | 215.5775 |
| 5.2125 | 0.7414 | 3500 | 5.0666 | 47.6221 | 14.2392 | 31.788 | 44.2768 | 79.9394 | 82.2162 | 81.0575 | 0.0954 | 215.5775 |
| 5.2604 | 0.8473 | 4000 | 5.0372 | 47.5699 | 14.3045 | 31.92 | 44.208 | 80.008 | 82.2777 | 81.1227 | 0.0967 | 215.5775 |
| 5.2959 | 0.9533 | 4500 | 5.0232 | 47.6658 | 14.3424 | 32.0036 | 44.3129 | 80.0039 | 82.2832 | 81.1232 | 0.0968 | 215.5775 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Library
- transformers
- Type
- pegasus
- Created
- Jun 9, 2024
- Updated
- Jun 9, 2024