End of training5
Browse files- README.md +9 -14
- pytorch_model.bin +1 -1
README.md
CHANGED
@@ -20,7 +20,7 @@ model-index:
|
|
20 |
metrics:
|
21 |
- name: Matthews Correlation
|
22 |
type: matthews_correlation
|
23 |
-
value: 0.
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,8 +30,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
This model was trained from scratch on the glue dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
-
- Loss:
|
34 |
-
- Matthews Correlation: 0.
|
35 |
|
36 |
## Model description
|
37 |
|
@@ -56,22 +56,17 @@ The following hyperparameters were used during training:
|
|
56 |
- seed: 42
|
57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
- lr_scheduler_type: linear
|
59 |
-
- num_epochs:
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
64 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.4225 | 6.0 | 3210 | 0.5946 | 0.3361 |
|
71 |
-
| 0.3937 | 7.0 | 3745 | 0.6147 | 0.3565 |
|
72 |
-
| 0.3841 | 8.0 | 4280 | 0.5999 | 0.3582 |
|
73 |
-
| 0.3816 | 9.0 | 4815 | 0.6317 | 0.3592 |
|
74 |
-
| 0.3726 | 10.0 | 5350 | 0.6230 | 0.3748 |
|
75 |
|
76 |
|
77 |
### Framework versions
|
|
|
20 |
metrics:
|
21 |
- name: Matthews Correlation
|
22 |
type: matthews_correlation
|
23 |
+
value: 0.5757702121003263
|
24 |
---
|
25 |
|
26 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
This model was trained from scratch on the glue dataset.
|
32 |
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 1.0491
|
34 |
+
- Matthews Correlation: 0.5758
|
35 |
|
36 |
## Model description
|
37 |
|
|
|
56 |
- seed: 42
|
57 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
58 |
- lr_scheduler_type: linear
|
59 |
+
- num_epochs: 5
|
60 |
|
61 |
### Training results
|
62 |
|
63 |
| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
|
64 |
|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
|
65 |
+
| 0.1532 | 1.0 | 535 | 0.9255 | 0.5757 |
|
66 |
+
| 0.1194 | 2.0 | 1070 | 0.9947 | 0.5653 |
|
67 |
+
| 0.098 | 3.0 | 1605 | 0.9838 | 0.5771 |
|
68 |
+
| 0.0915 | 4.0 | 2140 | 1.0381 | 0.5758 |
|
69 |
+
| 0.0857 | 5.0 | 2675 | 1.0491 | 0.5758 |
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
|
72 |
### Framework versions
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 433315633
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bf422f5fbb64ec8da0cf22595fa6cccc0b9fc1bd0c22d4dc2882f6d56bfb16c
|
3 |
size 433315633
|