Downloads · 30 days
7
3% of all-time downloads
mt5-small-finetuned-25feb-3
mqy/mt5-small-finetuned-25feb-3
mt5-small-finetuned-25feb-3 is a summarization model from mqy. Use it when you need a shorter version of a longer text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
219
Public
Repo size
20.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.2 GB · 98%
At a glance
- Task
- Summarization
- Library
- transformers
- License
- apache-2.0
- Model type
- mt5
- Access
- Public
- Created
- Feb 25, 2023
- Updated
- Feb 25, 2023
- SHA
- 4184801c
Try a prompt
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. -->
mt5-small-finetuned-25feb-3
This model is a fine-tuned version of google/mt5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3532
- Rouge1: 20.83
- Rouge2: 6.54
- Rougel: 20.4
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: 9
- eval_batch_size: 9
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 5.3088 | 1.45 | 500 | 2.6216 | 17.35 | 5.18 | 17.14 |
| 3.2982 | 2.9 | 1000 | 2.5396 | 17.76 | 5.55 | 17.53 |
| 2.9211 | 4.35 | 1500 | 2.4802 | 18.72 | 5.62 | 18.47 |
| 2.8162 | 5.8 | 2000 | 2.4158 | 18.16 | 5.26 | 17.7 |
| 2.6661 | 7.25 | 2500 | 2.4387 | 18.59 | 5.38 | 18.21 |
| 2.6102 | 8.7 | 3000 | 2.4044 | 19.54 | 5.63 | 19.16 |
| 2.5043 | 10.14 | 3500 | 2.3738 | 19.65 | 5.79 | 19.16 |
| 2.4598 | 11.59 | 4000 | 2.3805 | 19.86 | 6.29 | 19.43 |
| 2.3807 | 13.04 | 4500 | 2.3590 | 20.13 | 5.91 | 19.62 |
| 2.3461 | 14.49 | 5000 | 2.3611 | 20.73 | 6.28 | 20.31 |
| 2.3024 | 15.94 | 5500 | 2.3571 | 20.64 | 6.12 | 20.25 |
| 2.2704 | 17.39 | 6000 | 2.3723 | 19.71 | 5.95 | 19.35 |
| 2.2356 | 18.84 | 6500 | 2.3532 | 20.83 | 6.54 | 20.4 |
| 2.2019 | 20.29 | 7000 | 2.3597 | 19.67 | 5.91 | 19.28 |
| 2.1646 | 21.74 | 7500 | 2.3733 | 20.63 | 6.53 | 20.24 |
| 2.1511 | 23.19 | 8000 | 2.3534 | 20.63 | 6.22 | 20.22 |
| 2.128 | 24.64 | 8500 | 2.3552 | 20.12 | 5.92 | 19.77 |
| 2.0933 | 26.09 | 9000 | 2.3587 | 20.53 | 5.88 | 20.06 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.0
- Tokenizers 0.13.2
- Task
- Summarization
- Library
- transformers
- Type
- mt5
- License
- apache-2.0
- Created
- Feb 25, 2023
- Updated
- Feb 25, 2023