Downloads · 30 days
26
65% of all-time downloads
t5-moe-top4-4-mrpc
lightsout19/t5-moe-top4-4-mrpc
t5-moe-top4-4-mrpc is a machine learning model from lightsout19. 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
40
Public
Parameters
224M
4.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors895 MB · 100%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024
- SHA
- 30f9e47c
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. -->
t5-moe-top4-4-mrpc
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5850
- Accuracy: 0.7059
- F1: 0.8154
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 230 | 0.5956 | 0.6985 | 0.8145 |
| No log | 2.0 | 460 | 0.5857 | 0.7034 | 0.8136 |
| 0.6287 | 3.0 | 690 | 0.6120 | 0.6936 | 0.7863 |
| 0.6287 | 4.0 | 920 | 0.7940 | 0.6936 | 0.7878 |
| 0.4179 | 5.0 | 1150 | 1.0055 | 0.6765 | 0.7574 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0
- Library
- transformers
- Type
- t5
- Created
- Nov 7, 2024
- Updated
- Nov 7, 2024