update model card README.md
Browse files
README.md
CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 3.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,32 +39,20 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
-
| No log | 1.0 | 21 | 3.
|
49 |
-
| No log | 2.0 | 42 | 3.
|
50 |
-
| No log | 3.0 | 63 | 3.
|
51 |
-
| No log | 4.0 | 84 | 3.
|
52 |
-
| No log | 5.0 | 105 | 3.
|
53 |
-
| No log | 6.0 | 126 | 3.
|
54 |
-
| No log | 7.0 | 147 |
|
55 |
-
| No log | 8.0 | 168 | 3.
|
56 |
-
| No log | 9.0 | 189 | 3.1540 |
|
57 |
-
| No log | 10.0 | 210 | 3.4559 |
|
58 |
-
| No log | 11.0 | 231 | 3.5064 |
|
59 |
-
| No log | 12.0 | 252 | 3.7371 |
|
60 |
-
| No log | 13.0 | 273 | 3.7140 |
|
61 |
-
| No log | 14.0 | 294 | 3.7878 |
|
62 |
-
| No log | 15.0 | 315 | 3.8032 |
|
63 |
-
| No log | 16.0 | 336 | 3.7973 |
|
64 |
-
| No log | 17.0 | 357 | 3.8729 |
|
65 |
-
| No log | 18.0 | 378 | 3.9404 |
|
66 |
-
| No log | 19.0 | 399 | 3.9781 |
|
67 |
-
| No log | 20.0 | 420 | 3.9589 |
|
68 |
|
69 |
|
70 |
### Framework versions
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 3.1602
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 8
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:----:|:---------------:|
|
48 |
+
| No log | 1.0 | 21 | 3.3780 |
|
49 |
+
| No log | 2.0 | 42 | 3.2694 |
|
50 |
+
| No log | 3.0 | 63 | 3.1892 |
|
51 |
+
| No log | 4.0 | 84 | 3.1536 |
|
52 |
+
| No log | 5.0 | 105 | 3.1454 |
|
53 |
+
| No log | 6.0 | 126 | 3.1754 |
|
54 |
+
| No log | 7.0 | 147 | 3.1372 |
|
55 |
+
| No log | 8.0 | 168 | 3.1602 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|