update model card README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
-
- Loss: 3.
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -33,26 +33,71 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
- train_batch_size: 128
|
| 38 |
-
- eval_batch_size:
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
-
- lr_scheduler_type:
|
| 42 |
-
- num_epochs:
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
-
| Training Loss | Epoch | Step
|
| 47 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
-
|
|
| 49 |
-
| 4.
|
| 50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
-
- Transformers 4.
|
| 56 |
- Pytorch 1.12.1+cu113
|
| 57 |
- Datasets 2.7.1
|
| 58 |
- Tokenizers 0.13.2
|
|
|
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the None dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.4487
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 3e-05
|
| 37 |
- train_batch_size: 128
|
| 38 |
+
- eval_batch_size: 128
|
| 39 |
- seed: 42
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: constant
|
| 42 |
+
- num_epochs: 200
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 48 |
+
| 4.1774 | 1.04 | 500 | 3.7705 |
|
| 49 |
+
| 4.041 | 2.09 | 1000 | 3.7196 |
|
| 50 |
+
| 3.9982 | 3.13 | 1500 | 3.6826 |
|
| 51 |
+
| 3.9614 | 4.18 | 2000 | 3.6543 |
|
| 52 |
+
| 3.9274 | 5.22 | 2500 | 3.6438 |
|
| 53 |
+
| 3.9089 | 6.26 | 3000 | 3.6294 |
|
| 54 |
+
| 3.8929 | 7.31 | 3500 | 3.6217 |
|
| 55 |
+
| 3.873 | 8.35 | 4000 | 3.6083 |
|
| 56 |
+
| 3.8659 | 9.39 | 4500 | 3.5900 |
|
| 57 |
+
| 3.8484 | 10.44 | 5000 | 3.5791 |
|
| 58 |
+
| 3.8261 | 11.48 | 5500 | 3.5731 |
|
| 59 |
+
| 3.8228 | 12.53 | 6000 | 3.5579 |
|
| 60 |
+
| 3.8098 | 13.57 | 6500 | 3.5576 |
|
| 61 |
+
| 3.8028 | 14.61 | 7000 | 3.5532 |
|
| 62 |
+
| 3.7881 | 15.66 | 7500 | 3.5440 |
|
| 63 |
+
| 3.7829 | 16.7 | 8000 | 3.5440 |
|
| 64 |
+
| 3.7727 | 17.75 | 8500 | 3.5372 |
|
| 65 |
+
| 3.7648 | 18.79 | 9000 | 3.5248 |
|
| 66 |
+
| 3.7504 | 19.83 | 9500 | 3.5223 |
|
| 67 |
+
| 3.7487 | 20.88 | 10000 | 3.5212 |
|
| 68 |
+
| 3.7497 | 21.92 | 10500 | 3.5166 |
|
| 69 |
+
| 3.7344 | 22.96 | 11000 | 3.5103 |
|
| 70 |
+
| 3.7339 | 24.01 | 11500 | 3.5052 |
|
| 71 |
+
| 3.722 | 25.05 | 12000 | 3.5067 |
|
| 72 |
+
| 3.7188 | 26.1 | 12500 | 3.4941 |
|
| 73 |
+
| 3.7127 | 27.14 | 13000 | 3.4951 |
|
| 74 |
+
| 3.7113 | 28.18 | 13500 | 3.4904 |
|
| 75 |
+
| 3.7042 | 29.23 | 14000 | 3.4813 |
|
| 76 |
+
| 3.7011 | 30.27 | 14500 | 3.4805 |
|
| 77 |
+
| 3.6936 | 31.32 | 15000 | 3.4886 |
|
| 78 |
+
| 3.6889 | 32.36 | 15500 | 3.4825 |
|
| 79 |
+
| 3.6771 | 33.4 | 16000 | 3.4785 |
|
| 80 |
+
| 3.6753 | 34.45 | 16500 | 3.4819 |
|
| 81 |
+
| 3.6743 | 35.49 | 17000 | 3.4744 |
|
| 82 |
+
| 3.6686 | 36.53 | 17500 | 3.4658 |
|
| 83 |
+
| 3.669 | 37.58 | 18000 | 3.4607 |
|
| 84 |
+
| 3.6623 | 38.62 | 18500 | 3.4688 |
|
| 85 |
+
| 3.6648 | 39.67 | 19000 | 3.4676 |
|
| 86 |
+
| 3.6574 | 40.71 | 19500 | 3.4581 |
|
| 87 |
+
| 3.652 | 41.75 | 20000 | 3.4601 |
|
| 88 |
+
| 3.6506 | 42.8 | 20500 | 3.4630 |
|
| 89 |
+
| 3.6466 | 43.84 | 21000 | 3.4530 |
|
| 90 |
+
| 3.637 | 44.89 | 21500 | 3.4507 |
|
| 91 |
+
| 3.6428 | 45.93 | 22000 | 3.4557 |
|
| 92 |
+
| 3.6408 | 46.97 | 22500 | 3.4483 |
|
| 93 |
+
| 3.6368 | 48.02 | 23000 | 3.4505 |
|
| 94 |
+
| 3.6322 | 49.06 | 23500 | 3.4494 |
|
| 95 |
+
| 3.6256 | 50.1 | 24000 | 3.4487 |
|
| 96 |
|
| 97 |
|
| 98 |
### Framework versions
|
| 99 |
|
| 100 |
+
- Transformers 4.25.1
|
| 101 |
- Pytorch 1.12.1+cu113
|
| 102 |
- Datasets 2.7.1
|
| 103 |
- Tokenizers 0.13.2
|