Commit
•
df3589a
1
Parent(s):
8394184
End of training
Browse files
README.md
CHANGED
@@ -5,6 +5,7 @@ tags:
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
|
|
8 |
model-index:
|
9 |
- name: c4-binary-english-grammar-checker
|
10 |
results: []
|
@@ -17,8 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Accuracy: 0.
|
|
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,17 +45,14 @@ 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
|
51 |
-
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.2939 | 3.0 | 37500 | 0.5059 | 0.8174 |
|
55 |
-
| 0.2327 | 4.0 | 50000 | 0.6280 | 0.8081 |
|
56 |
-
| 0.1822 | 5.0 | 62500 | 0.7704 | 0.8103 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
5 |
- generated_from_trainer
|
6 |
metrics:
|
7 |
- accuracy
|
8 |
+
- matthews_correlation
|
9 |
model-index:
|
10 |
- name: c4-binary-english-grammar-checker
|
11 |
results: []
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.3546
|
22 |
+
- Accuracy: 0.8577
|
23 |
+
- Matthews Correlation: 0.7192
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 2
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Matthews Correlation |
|
53 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:--------------------:|
|
54 |
+
| 0.363 | 1.0 | 200000 | 0.3634 | 0.8487 | 0.7025 |
|
55 |
+
| 0.3032 | 2.0 | 400000 | 0.3546 | 0.8577 | 0.7192 |
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|