Downloads · 30 days
6
15% of all-time downloads
fine-tune_simcse-ise-dsc
nhatnv0378/fine-tune_simcse-ise-dsc
fine-tune_simcse-ise-dsc is a fill-mask model from nhatnv0378. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
41
Public
Repo size
2.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin540 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Oct 15, 2023
- Updated
- Oct 15, 2023
- SHA
- 93a24a1c
Try a prompt
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. -->
fine-tune_simcse-ise-dsc
This model is a fine-tuned version of dalietng/fine-tune_simcse on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.1557
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.6521 | 1.0 | 150 | 6.5226 |
| 6.2495 | 2.0 | 300 | 5.7732 |
| 5.7165 | 3.0 | 450 | 5.3397 |
| 5.3248 | 4.0 | 600 | 4.9877 |
| 5.0048 | 5.0 | 750 | 4.6467 |
| 4.7731 | 6.0 | 900 | 4.4911 |
| 4.6241 | 7.0 | 1050 | 4.3463 |
| 4.5002 | 8.0 | 1200 | 4.2555 |
| 4.4253 | 9.0 | 1350 | 4.1877 |
| 4.3888 | 10.0 | 1500 | 4.1762 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- Oct 15, 2023
- Updated
- Oct 15, 2023