Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: dascim/juribert-tiny
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: bert-secabilite-regressor
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# bert-secabilite-regressor
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [dascim/juribert-tiny](https://huggingface.co/dascim/juribert-tiny) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0257
|
| 20 |
+
- Model Preparation Time: 0.0006
|
| 21 |
+
- Mse: 0.0258
|
| 22 |
+
- Mae: 0.1103
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 3e-05
|
| 42 |
+
- train_batch_size: 8
|
| 43 |
+
- eval_batch_size: 8
|
| 44 |
+
- seed: 42
|
| 45 |
+
- gradient_accumulation_steps: 4
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
+
- lr_scheduler_type: linear
|
| 49 |
+
- num_epochs: 8
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Mse | Mae |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:------:|:------:|
|
| 55 |
+
| 0.0928 | 1.0 | 108 | 0.0562 | 0.0006 | 0.0563 | 0.1906 |
|
| 56 |
+
| 0.0531 | 2.0 | 216 | 0.0379 | 0.0006 | 0.0380 | 0.1462 |
|
| 57 |
+
| 0.0427 | 3.0 | 324 | 0.0314 | 0.0006 | 0.0316 | 0.1292 |
|
| 58 |
+
| 0.037 | 4.0 | 432 | 0.0285 | 0.0006 | 0.0286 | 0.1205 |
|
| 59 |
+
| 0.0342 | 5.0 | 540 | 0.0272 | 0.0006 | 0.0273 | 0.1157 |
|
| 60 |
+
| 0.0321 | 6.0 | 648 | 0.0263 | 0.0006 | 0.0264 | 0.1127 |
|
| 61 |
+
| 0.0311 | 7.0 | 756 | 0.0259 | 0.0006 | 0.0260 | 0.1109 |
|
| 62 |
+
| 0.0306 | 8.0 | 864 | 0.0257 | 0.0006 | 0.0258 | 0.1103 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 4.51.3
|
| 68 |
+
- Pytorch 2.7.0
|
| 69 |
+
- Datasets 3.5.0
|
| 70 |
+
- Tokenizers 0.21.1
|