Commit
•
8c36c0e
1
Parent(s):
5266ec5
update model card README.md
Browse files
README.md
CHANGED
|
@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
-
- Precision: 0.
|
| 24 |
- Recall: 0.2
|
| 25 |
-
- F1: 0.
|
| 26 |
-
- Accuracy: 0.
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -48,29 +48,20 @@ The following hyperparameters were used during training:
|
|
| 48 |
- seed: 42
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
-
- num_epochs:
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
-
| No log | 1.0 | 19 | 1.
|
| 58 |
-
| No log | 2.0 | 38 | 1.
|
| 59 |
-
| No log | 3.0 | 57 |
|
| 60 |
-
| No log | 4.0 | 76 | 3.1633 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 61 |
-
| No log | 5.0 | 95 | 3.3965 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 62 |
-
| No log | 6.0 | 114 | 3.5159 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 63 |
-
| No log | 7.0 | 133 | 3.6268 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 64 |
-
| No log | 8.0 | 152 | 3.7452 | 0.1667 | 0.2 | 0.1818 | 0.5185 |
|
| 65 |
-
| No log | 9.0 | 171 | 3.7567 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 66 |
-
| No log | 10.0 | 190 | 3.7692 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 67 |
-
| No log | 11.0 | 209 | 3.7870 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 68 |
-
| No log | 12.0 | 228 | 3.7940 | 0.1538 | 0.2 | 0.1739 | 0.5278 |
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
| 72 |
|
| 73 |
-
- Transformers 4.16.
|
| 74 |
- Pytorch 1.10.0+cu111
|
| 75 |
-
- Datasets 1.18.
|
| 76 |
- Tokenizers 0.11.0
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 1.6497
|
| 23 |
+
- Precision: 0.1818
|
| 24 |
- Recall: 0.2
|
| 25 |
+
- F1: 0.1905
|
| 26 |
+
- Accuracy: 0.5093
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
|
|
| 48 |
- seed: 42
|
| 49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 3
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 57 |
+
| No log | 1.0 | 19 | 1.3083 | 0.0 | 0.0 | 0.0 | 0.3981 |
|
| 58 |
+
| No log | 2.0 | 38 | 1.5496 | 0.2222 | 0.2 | 0.2105 | 0.4907 |
|
| 59 |
+
| No log | 3.0 | 57 | 1.6497 | 0.1818 | 0.2 | 0.1905 | 0.5093 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
|
| 62 |
### Framework versions
|
| 63 |
|
| 64 |
+
- Transformers 4.16.1
|
| 65 |
- Pytorch 1.10.0+cu111
|
| 66 |
+
- Datasets 1.18.2
|
| 67 |
- Tokenizers 0.11.0
|