update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Matthews Correlation
|
23 |
type: matthews_correlation
|
24 |
-
value: 0.
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss: 0.
|
35 |
-
- Matthews Correlation: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -57,17 +57,14 @@ The following hyperparameters were used during training:
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
-
- num_epochs:
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.2351 | 3.0 | 1605 | 0.5809 | 0.5140 |
|
69 |
-
| 0.1742 | 4.0 | 2140 | 0.7780 | 0.5301 |
|
70 |
-
| 0.1226 | 5.0 | 2675 | 0.8545 | 0.5480 |
|
71 |
|
72 |
|
73 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Matthews Correlation
|
23 |
type: matthews_correlation
|
24 |
+
value: 0.4927793660353066
|
25 |
---
|
26 |
|
27 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
31 |
|
32 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the glue dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 0.5040
|
35 |
+
- Matthews Correlation: 0.4928
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
57 |
- seed: 42
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 2
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
66 |
+
| 0.523 | 1.0 | 535 | 0.5027 | 0.4210 |
|
67 |
+
| 0.3553 | 2.0 | 1070 | 0.5040 | 0.4928 |
|
|
|
|
|
|
|
68 |
|
69 |
|
70 |
### Framework versions
|