Commit ·
5fc4b7a
1
Parent(s): 512549a
End of training
Browse files
README.md
CHANGED
|
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy: 0.
|
| 23 |
-
- F1: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -46,14 +46,15 @@ The following hyperparameters were used during training:
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 500
|
| 49 |
-
- num_epochs:
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
|
|
|
| 57 |
|
| 58 |
|
| 59 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4362
|
| 22 |
+
- Accuracy: 0.8056
|
| 23 |
+
- F1: 0.8066
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 500
|
| 49 |
+
- num_epochs: 3
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 54 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|
|
| 55 |
+
| 0.4436 | 1.0 | 6787 | 0.4530 | 0.7934 | 0.7896 |
|
| 56 |
+
| 0.4519 | 2.0 | 13574 | 0.4363 | 0.8016 | 0.7982 |
|
| 57 |
+
| 0.4187 | 3.0 | 20361 | 0.4362 | 0.8056 | 0.8066 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|