Commit
•
ebc0f47
1
Parent(s):
038cb71
update model card README.md
Browse files
README.md
CHANGED
|
@@ -13,7 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [NlpHUST/electra-base-vn](https://huggingface.co/NlpHUST/electra-base-vn) on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
@@ -32,7 +37,7 @@ More information needed
|
|
| 32 |
### Training hyperparameters
|
| 33 |
|
| 34 |
The following hyperparameters were used during training:
|
| 35 |
-
- learning_rate:
|
| 36 |
- train_batch_size: 12
|
| 37 |
- eval_batch_size: 12
|
| 38 |
- seed: 42
|
|
@@ -40,22 +45,6 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_type: linear
|
| 41 |
- num_epochs: 10
|
| 42 |
|
| 43 |
-
### Training results
|
| 44 |
-
|
| 45 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 46 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
| 47 |
-
| 1.7588 | 1.0 | 1912 | 1.5902 |
|
| 48 |
-
| 1.2695 | 2.0 | 3824 | 1.4278 |
|
| 49 |
-
| 0.9466 | 3.0 | 5736 | 1.4897 |
|
| 50 |
-
| 0.7172 | 4.0 | 7648 | 1.7142 |
|
| 51 |
-
| 0.5232 | 5.0 | 9560 | 1.9696 |
|
| 52 |
-
| 0.4025 | 6.0 | 11472 | 2.2235 |
|
| 53 |
-
| 0.3104 | 7.0 | 13384 | 2.4544 |
|
| 54 |
-
| 0.243 | 8.0 | 15296 | 2.7552 |
|
| 55 |
-
| 0.1863 | 9.0 | 17208 | 2.9858 |
|
| 56 |
-
| 0.1531 | 10.0 | 19120 | 3.0900 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
- Transformers 4.23.0.dev0
|
|
|
|
| 13 |
|
| 14 |
This model is a fine-tuned version of [NlpHUST/electra-base-vn](https://huggingface.co/NlpHUST/electra-base-vn) on the None dataset.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
+
- eval_loss: 1.5498
|
| 17 |
+
- eval_runtime: 98.1124
|
| 18 |
+
- eval_samples_per_second: 58.474
|
| 19 |
+
- eval_steps_per_second: 4.882
|
| 20 |
+
- epoch: 4.0
|
| 21 |
+
- step: 7648
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
- train_batch_size: 12
|
| 42 |
- eval_batch_size: 12
|
| 43 |
- seed: 42
|
|
|
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- num_epochs: 10
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.23.0.dev0
|