Commit
•
3c61715
1
Parent(s):
ed4e1ff
update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the squad_modified_for_t5_qg dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 1.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -43,32 +43,26 @@ The following hyperparameters were used during training:
|
|
| 43 |
- total_train_batch_size: 64
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
-
- num_epochs:
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
-
| 2.
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
| 1.
|
| 56 |
-
| 1.
|
| 57 |
-
| 1.
|
| 58 |
-
| 1.
|
| 59 |
-
| 1.
|
| 60 |
-
| 1.
|
| 61 |
-
| 1.
|
| 62 |
-
| 1.
|
| 63 |
-
| 1.
|
| 64 |
-
| 1.
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.524 | 5.08 | 1500 | 1.5727 |
|
| 67 |
-
| 1.4954 | 5.42 | 1600 | 1.5699 |
|
| 68 |
-
| 1.4866 | 5.76 | 1700 | 1.5696 |
|
| 69 |
-
| 1.5089 | 6.1 | 1800 | 1.5696 |
|
| 70 |
-
| 1.4771 | 6.44 | 1900 | 1.5736 |
|
| 71 |
-
| 1.4772 | 6.78 | 2000 | 1.5679 |
|
| 72 |
|
| 73 |
|
| 74 |
### Framework versions
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the squad_modified_for_t5_qg dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.5789
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 43 |
- total_train_batch_size: 64
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 5
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 2.5879 | 0.34 | 100 | 1.9133 |
|
| 53 |
+
| 1.9688 | 0.68 | 200 | 1.7313 |
|
| 54 |
+
| 1.8513 | 1.02 | 300 | 1.6691 |
|
| 55 |
+
| 1.7459 | 1.36 | 400 | 1.6413 |
|
| 56 |
+
| 1.7206 | 1.69 | 500 | 1.6200 |
|
| 57 |
+
| 1.7026 | 2.03 | 600 | 1.6101 |
|
| 58 |
+
| 1.6447 | 2.37 | 700 | 1.5983 |
|
| 59 |
+
| 1.6402 | 2.71 | 800 | 1.5979 |
|
| 60 |
+
| 1.6332 | 3.05 | 900 | 1.5924 |
|
| 61 |
+
| 1.5953 | 3.39 | 1000 | 1.5877 |
|
| 62 |
+
| 1.5922 | 3.73 | 1100 | 1.5854 |
|
| 63 |
+
| 1.5832 | 4.07 | 1200 | 1.5830 |
|
| 64 |
+
| 1.5726 | 4.41 | 1300 | 1.5799 |
|
| 65 |
+
| 1.5587 | 4.75 | 1400 | 1.5789 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|