update model card README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ model-index:
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
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 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -52,20 +52,22 @@ More information needed
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 5e-05
|
55 |
-
- train_batch_size:
|
56 |
-
- eval_batch_size:
|
57 |
-
- seed:
|
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 | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
-
| No log | 1.0 |
|
67 |
-
| No log | 2.0 |
|
68 |
-
| No log | 3.0 |
|
|
|
|
|
69 |
|
70 |
|
71 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.8623529411764705
|
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: 0.4654
|
35 |
+
- Accuracy: 0.8624
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 32
|
56 |
+
- eval_batch_size: 32
|
57 |
+
- seed: 30
|
58 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 5
|
61 |
|
62 |
### Training results
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| No log | 1.0 | 27 | 0.4003 | 0.8224 |
|
67 |
+
| No log | 2.0 | 54 | 0.3516 | 0.8459 |
|
68 |
+
| No log | 3.0 | 81 | 0.4151 | 0.8376 |
|
69 |
+
| No log | 4.0 | 108 | 0.4419 | 0.8635 |
|
70 |
+
| No log | 5.0 | 135 | 0.4654 | 0.8624 |
|
71 |
|
72 |
|
73 |
### Framework versions
|