Commit
•
fa60a7a
1
Parent(s):
160f64d
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
model-index:
|
| 7 |
+
- name: hebert-finetuned-hebrew-metaphor
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# hebert-finetuned-hebrew-metaphor
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [avichr/heBERT](https://huggingface.co/avichr/heBERT) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4682
|
| 19 |
+
- Accuracy: 0.9510
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- num_epochs: 15
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 50 |
+
| No log | 1.0 | 389 | 0.1813 | 0.9379 |
|
| 51 |
+
| 0.2546 | 2.0 | 778 | 0.2309 | 0.9479 |
|
| 52 |
+
| 0.08 | 3.0 | 1167 | 0.3342 | 0.9492 |
|
| 53 |
+
| 0.0298 | 4.0 | 1556 | 0.4076 | 0.9460 |
|
| 54 |
+
| 0.0298 | 5.0 | 1945 | 0.3803 | 0.9485 |
|
| 55 |
+
| 0.0105 | 6.0 | 2334 | 0.3674 | 0.9454 |
|
| 56 |
+
| 0.0077 | 7.0 | 2723 | 0.5356 | 0.9410 |
|
| 57 |
+
| 0.0088 | 8.0 | 3112 | 0.4776 | 0.9422 |
|
| 58 |
+
| 0.0044 | 9.0 | 3501 | 0.4258 | 0.9504 |
|
| 59 |
+
| 0.0044 | 10.0 | 3890 | 0.4305 | 0.9523 |
|
| 60 |
+
| 0.001 | 11.0 | 4279 | 0.4357 | 0.9548 |
|
| 61 |
+
| 0.0031 | 12.0 | 4668 | 0.4770 | 0.9473 |
|
| 62 |
+
| 0.0015 | 13.0 | 5057 | 0.4604 | 0.9523 |
|
| 63 |
+
| 0.0015 | 14.0 | 5446 | 0.4670 | 0.9510 |
|
| 64 |
+
| 0.0022 | 15.0 | 5835 | 0.4682 | 0.9510 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.30.2
|
| 70 |
+
- Pytorch 2.0.1+cu118
|
| 71 |
+
- Datasets 2.13.1
|
| 72 |
+
- Tokenizers 0.13.3
|