timewanderer
commited on
Commit
•
45108bd
1
Parent(s):
bedb30d
Training complete!
Browse files
README.md
CHANGED
@@ -18,8 +18,8 @@ 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 an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
-
| No log | 1.0 | 318 | 1.
|
54 |
-
|
|
55 |
-
|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2209
|
22 |
+
- Accuracy: 0.9471
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
53 |
+
| No log | 1.0 | 318 | 1.8516 | 0.7474 |
|
54 |
+
| 2.1784 | 2.0 | 636 | 0.9798 | 0.8771 |
|
55 |
+
| 2.1784 | 3.0 | 954 | 0.5581 | 0.9148 |
|
56 |
+
| 0.8727 | 4.0 | 1272 | 0.3767 | 0.9326 |
|
57 |
+
| 0.381 | 5.0 | 1590 | 0.2928 | 0.9426 |
|
58 |
+
| 0.381 | 6.0 | 1908 | 0.2570 | 0.9435 |
|
59 |
+
| 0.2238 | 7.0 | 2226 | 0.2370 | 0.9465 |
|
60 |
+
| 0.1683 | 8.0 | 2544 | 0.2273 | 0.9465 |
|
61 |
+
| 0.1683 | 9.0 | 2862 | 0.2221 | 0.9468 |
|
62 |
+
| 0.1478 | 10.0 | 3180 | 0.2209 | 0.9471 |
|
63 |
|
64 |
|
65 |
### Framework versions
|