Downloads · 30 days
10
22% of all-time downloads
GeneralNews_1_loadbest
tjkmitl/GeneralNews_1_loadbest
GeneralNews_1_loadbest is a machine learning model from tjkmitl. 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
46
Public
Parameters
582M
2.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.3 GB · 99%
At a glance
- Library
- transformers
- Model type
- mt5
- Access
- Public
- Created
- Feb 1, 2024
- Updated
- Feb 1, 2024
- SHA
- ca0cd184
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. -->
GeneralNews_1_loadbest
This model is a fine-tuned version of csebuetnlp/mT5_multilingual_XLSum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9834
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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1541 | 0.25 | 200 | 3.4209 |
| 3.5494 | 0.51 | 400 | 3.1702 |
| 3.2618 | 0.76 | 600 | 3.0273 |
| 3.5983 | 1.01 | 800 | 2.9550 |
| 3.3355 | 1.26 | 1000 | 2.8883 |
| 3.4976 | 1.52 | 1200 | 2.8653 |
| 3.1001 | 1.77 | 1400 | 2.8543 |
| 2.282 | 2.02 | 1600 | 2.7953 |
| 2.5724 | 2.27 | 1800 | 2.7866 |
| 2.7474 | 2.53 | 2000 | 2.7778 |
| 3.0323 | 2.78 | 2200 | 2.7901 |
| 2.3032 | 3.03 | 2400 | 2.7641 |
| 2.5042 | 3.28 | 2600 | 2.8059 |
| 1.9857 | 3.54 | 2800 | 2.7847 |
| 2.5909 | 3.79 | 3000 | 2.8045 |
| 2.2105 | 4.04 | 3200 | 2.8051 |
| 2.1151 | 4.29 | 3400 | 2.8331 |
| 1.9858 | 4.55 | 3600 | 2.8292 |
| 1.9633 | 4.8 | 3800 | 2.8133 |
| 2.0282 | 5.05 | 4000 | 2.8317 |
| 2.0988 | 5.3 | 4200 | 2.8781 |
| 2.0699 | 5.56 | 4400 | 2.8627 |
| 2.1769 | 5.81 | 4600 | 2.8388 |
| 1.7436 | 6.06 | 4800 | 2.8899 |
| 1.8312 | 6.31 | 5000 | 2.9223 |
| 1.841 | 6.57 | 5200 | 2.8970 |
| 2.0157 | 6.82 | 5400 | 2.8754 |
| 2.1223 | 7.07 | 5600 | 2.8958 |
| 1.6103 | 7.32 | 5800 | 2.9247 |
| 1.7702 | 7.58 | 6000 | 2.9562 |
| 1.537 | 7.83 | 6200 | 2.9597 |
| 1.933 | 8.08 | 6400 | 2.9585 |
| 1.3947 | 8.33 | 6600 | 2.9841 |
| 1.639 | 8.59 | 6800 | 2.9723 |
| 1.6441 | 8.84 | 7000 | 2.9770 |
| 1.4509 | 9.09 | 7200 | 2.9865 |
| 1.6212 | 9.34 | 7400 | 2.9890 |
| 1.8013 | 9.6 | 7600 | 2.9877 |
| 1.3722 | 9.85 | 7800 | 2.9834 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1
- Library
- transformers
- Type
- mt5
- Created
- Feb 1, 2024
- Updated
- Feb 1, 2024