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 [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the emotion dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -47,22 +47,22 @@ The following hyperparameters were used during training:
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 0.
|
51 |
-
| 0.
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
|
67 |
|
68 |
### Framework versions
|
16 |
|
17 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the emotion dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.2748
|
20 |
|
21 |
## Model description
|
22 |
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 0.9063 | 0.25 | 500 | 0.4845 |
|
51 |
+
| 0.3362 | 0.5 | 1000 | 0.3492 |
|
52 |
+
| 0.2759 | 0.75 | 1500 | 0.2819 |
|
53 |
+
| 0.2521 | 1.0 | 2000 | 0.2464 |
|
54 |
+
| 0.1705 | 1.25 | 2500 | 0.2345 |
|
55 |
+
| 0.1841 | 1.5 | 3000 | 0.2013 |
|
56 |
+
| 0.1428 | 1.75 | 3500 | 0.1926 |
|
57 |
+
| 0.1747 | 2.0 | 4000 | 0.1866 |
|
58 |
+
| 0.1082 | 2.25 | 4500 | 0.2302 |
|
59 |
+
| 0.1142 | 2.5 | 5000 | 0.2118 |
|
60 |
+
| 0.1205 | 2.75 | 5500 | 0.2318 |
|
61 |
+
| 0.1135 | 3.0 | 6000 | 0.2306 |
|
62 |
+
| 0.0803 | 3.25 | 6500 | 0.2625 |
|
63 |
+
| 0.0745 | 3.5 | 7000 | 0.2850 |
|
64 |
+
| 0.085 | 3.75 | 7500 | 0.2719 |
|
65 |
+
| 0.0701 | 4.0 | 8000 | 0.2748 |
|
66 |
|
67 |
|
68 |
### Framework versions
|