Downloads · 30 days
6
13% of all-time downloads
emoBank_LaBSE_test2_epochs_20
dgalik/emoBank_LaBSE_test2_epochs_20
emoBank_LaBSE_test2_epochs_20 is a machine learning model from dgalik. 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
47
Public
Repo size
18.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.9 GB · 100%
At a glance
- Library
- transformers
- Model type
- bert
- Access
- Public
- Created
- Sep 7, 2023
- Updated
- Sep 7, 2023
- SHA
- e0e873f1
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. -->
emoBank_LaBSE_test2_epochs_20
This model is a fine-tuned version of old_models/LaBSE/0_Transformer on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0470
- Mse V: 0.0563
- Mse A: 0.0484
- Mse D: 0.0363
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse V | Mse A | Mse D |
|---|---|---|---|---|---|---|
| No log | 1.0 | 252 | 0.0601 | 0.0677 | 0.0655 | 0.0472 |
| 0.194 | 2.0 | 504 | 0.0599 | 0.0895 | 0.0553 | 0.0348 |
| 0.194 | 3.0 | 756 | 0.0511 | 0.0524 | 0.0609 | 0.0399 |
| 0.0614 | 4.0 | 1008 | 0.0565 | 0.0719 | 0.0491 | 0.0485 |
| 0.0614 | 5.0 | 1260 | 0.0475 | 0.0661 | 0.0433 | 0.0331 |
| 0.0476 | 6.0 | 1512 | 0.0476 | 0.0561 | 0.0488 | 0.0380 |
| 0.0476 | 7.0 | 1764 | 0.0537 | 0.0587 | 0.0620 | 0.0405 |
| 0.0385 | 8.0 | 2016 | 0.0496 | 0.0543 | 0.0595 | 0.0350 |
| 0.0385 | 9.0 | 2268 | 0.0470 | 0.0563 | 0.0484 | 0.0363 |
| 0.033 | 10.0 | 2520 | 0.0503 | 0.0525 | 0.0585 | 0.0399 |
| 0.033 | 11.0 | 2772 | 0.0615 | 0.0700 | 0.0749 | 0.0396 |
| 0.028 | 12.0 | 3024 | 0.0509 | 0.0555 | 0.0593 | 0.0380 |
| 0.028 | 13.0 | 3276 | 0.0506 | 0.0572 | 0.0545 | 0.0400 |
| 0.0251 | 14.0 | 3528 | 0.0481 | 0.0537 | 0.0525 | 0.0382 |
| 0.0251 | 15.0 | 3780 | 0.0504 | 0.0512 | 0.0597 | 0.0404 |
| 0.0227 | 16.0 | 4032 | 0.0517 | 0.0580 | 0.0588 | 0.0383 |
| 0.0227 | 17.0 | 4284 | 0.0556 | 0.0541 | 0.0637 | 0.0490 |
| 0.0206 | 18.0 | 4536 | 0.0539 | 0.0595 | 0.0600 | 0.0422 |
| 0.0206 | 19.0 | 4788 | 0.0545 | 0.0571 | 0.0612 | 0.0453 |
| 0.0195 | 20.0 | 5040 | 0.0530 | 0.0563 | 0.0605 | 0.0423 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3
- Library
- transformers
- Type
- bert
- Created
- Sep 7, 2023
- Updated
- Sep 7, 2023