update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: gbert-large-finetuned-cust
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# gbert-large-finetuned-cust
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [deepset/gbert-large](https://huggingface.co/deepset/gbert-large) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.1846
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 2e-05
|
| 37 |
+
- train_batch_size: 32
|
| 38 |
+
- eval_batch_size: 32
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 30
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 0.8251 | 1.0 | 157 | 0.5204 |
|
| 50 |
+
| 0.508 | 2.0 | 314 | 0.3953 |
|
| 51 |
+
| 0.4009 | 3.0 | 471 | 0.3242 |
|
| 52 |
+
| 0.3587 | 4.0 | 628 | 0.3300 |
|
| 53 |
+
| 0.3276 | 5.0 | 785 | 0.3137 |
|
| 54 |
+
| 0.302 | 6.0 | 942 | 0.2826 |
|
| 55 |
+
| 0.2777 | 7.0 | 1099 | 0.2768 |
|
| 56 |
+
| 0.2609 | 8.0 | 1256 | 0.2726 |
|
| 57 |
+
| 0.244 | 9.0 | 1413 | 0.2660 |
|
| 58 |
+
| 0.2274 | 10.0 | 1570 | 0.2391 |
|
| 59 |
+
| 0.2132 | 11.0 | 1727 | 0.2353 |
|
| 60 |
+
| 0.2014 | 12.0 | 1884 | 0.2134 |
|
| 61 |
+
| 0.1835 | 13.0 | 2041 | 0.2278 |
|
| 62 |
+
| 0.1896 | 14.0 | 2198 | 0.2110 |
|
| 63 |
+
| 0.1974 | 15.0 | 2355 | 0.2132 |
|
| 64 |
+
| 0.1775 | 16.0 | 2512 | 0.1973 |
|
| 65 |
+
| 0.1715 | 17.0 | 2669 | 0.1941 |
|
| 66 |
+
| 0.1777 | 18.0 | 2826 | 0.2105 |
|
| 67 |
+
| 0.1741 | 19.0 | 2983 | 0.2127 |
|
| 68 |
+
| 0.1607 | 20.0 | 3140 | 0.1762 |
|
| 69 |
+
| 0.1562 | 21.0 | 3297 | 0.2095 |
|
| 70 |
+
| 0.1548 | 22.0 | 3454 | 0.1805 |
|
| 71 |
+
| 0.1534 | 23.0 | 3611 | 0.1852 |
|
| 72 |
+
| 0.1484 | 24.0 | 3768 | 0.1773 |
|
| 73 |
+
| 0.1473 | 25.0 | 3925 | 0.1759 |
|
| 74 |
+
| 0.1354 | 26.0 | 4082 | 0.1734 |
|
| 75 |
+
| 0.136 | 27.0 | 4239 | 0.1902 |
|
| 76 |
+
| 0.1306 | 28.0 | 4396 | 0.1769 |
|
| 77 |
+
| 0.1353 | 29.0 | 4553 | 0.1705 |
|
| 78 |
+
| 0.1368 | 30.0 | 4710 | 0.1846 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.28.1
|
| 84 |
+
- Pytorch 2.0.0+cu118
|
| 85 |
+
- Datasets 2.11.0
|
| 86 |
+
- Tokenizers 0.13.3
|