End of training
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,17 +43,23 @@ The following hyperparameters were used during training:
|
|
43 |
- seed: 42
|
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 | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
-
| No log | 1.0 | 10 | 0.
|
53 |
-
| No log | 2.0 | 20 | 0.
|
54 |
-
| No log | 3.0 | 30 | 0.
|
55 |
-
| No log | 4.0 | 40 | 0.
|
56 |
-
| No log | 5.0 | 50 | 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1180
|
21 |
+
- Accuracy: 0.9875
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 11
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
52 |
+
| No log | 1.0 | 10 | 0.8421 | 0.625 |
|
53 |
+
| No log | 2.0 | 20 | 0.7016 | 0.75 |
|
54 |
+
| No log | 3.0 | 30 | 0.5544 | 0.85 |
|
55 |
+
| No log | 4.0 | 40 | 0.4178 | 0.8938 |
|
56 |
+
| No log | 5.0 | 50 | 0.3177 | 0.9187 |
|
57 |
+
| No log | 6.0 | 60 | 0.2455 | 0.9187 |
|
58 |
+
| No log | 7.0 | 70 | 0.2007 | 0.9313 |
|
59 |
+
| No log | 8.0 | 80 | 0.1603 | 0.9563 |
|
60 |
+
| No log | 9.0 | 90 | 0.1396 | 0.975 |
|
61 |
+
| No log | 10.0 | 100 | 0.1243 | 0.9875 |
|
62 |
+
| No log | 11.0 | 110 | 0.1180 | 0.9875 |
|
63 |
|
64 |
|
65 |
### Framework versions
|