Downloads · 30 days
0
lang_adapter_fa_digikala_multilingual_base_cased
NightMachinery/lang_adapter_fa_digikala_multilingual_base_cased
lang_adapter_fa_digikala_multilingual_base_cased is a machine learning model from NightMachinery. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Mar 2, 2023
Repo size
8.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin375 MB · 99%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Mar 2, 2023
- Updated
- Mar 2, 2023
- SHA
- 8a3f9c30
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. -->
lang_adapter_fa_digikala_multilingual_base_cased
This model is a fine-tuned version of bert-base-multilingual-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8074
- Accuracy: 0.6254
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.7072 | 0.45 | 500 | 2.3782 | 0.5341 |
| 2.4037 | 0.9 | 1000 | 2.2189 | 0.5588 |
| 2.2792 | 1.35 | 1500 | 2.1282 | 0.5720 |
| 2.2017 | 1.8 | 2000 | 2.0641 | 0.5821 |
| 2.1322 | 2.25 | 2500 | 2.0273 | 0.5889 |
| 2.0955 | 2.7 | 3000 | 1.9950 | 0.5945 |
| 2.0673 | 3.15 | 3500 | 1.9655 | 0.6000 |
| 2.0399 | 3.6 | 4000 | 1.9462 | 0.6033 |
| 2.0148 | 4.05 | 4500 | 1.9300 | 0.6056 |
| 1.9987 | 4.5 | 5000 | 1.9113 | 0.6069 |
| 1.9824 | 4.95 | 5500 | 1.8823 | 0.6128 |
| 1.9704 | 5.41 | 6000 | 1.8824 | 0.6119 |
| 1.9502 | 5.86 | 6500 | 1.8701 | 0.6157 |
| 1.9527 | 6.31 | 7000 | 1.8497 | 0.6190 |
| 1.9217 | 6.76 | 7500 | 1.8493 | 0.6174 |
| 1.9091 | 7.21 | 8000 | 1.8341 | 0.6210 |
| 1.9095 | 7.66 | 8500 | 1.8145 | 0.6250 |
| 1.9107 | 8.11 | 9000 | 1.8320 | 0.6190 |
| 1.8929 | 8.56 | 9500 | 1.8051 | 0.6268 |
| 1.8855 | 9.01 | 10000 | 1.8257 | 0.6221 |
| 1.8893 | 9.46 | 10500 | 1.8206 | 0.6231 |
| 1.8899 | 9.91 | 11000 | 1.7972 | 0.6244 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.12.1
- License
- apache-2.0
- Created
- Mar 2, 2023
- Updated
- Mar 2, 2023