update model card README.md
Browse files
README.md
CHANGED
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the lex_glue dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Macro-f1: 0.
|
21 |
-
- Micro-f1: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -43,17 +43,15 @@ 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 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.1762 | 1.33 | 1500 | 0.2807 | 0.3945 | 0.5273 |
|
56 |
-
| 0.16 | 1.78 | 2000 | 0.2669 | 0.4193 | 0.5573 |
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the lex_glue dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.2487
|
20 |
+
- Macro-f1: 0.4052
|
21 |
+
- Micro-f1: 0.5660
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 1
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Macro-f1 | Micro-f1 |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
|
53 |
+
| 0.2056 | 0.44 | 500 | 0.2846 | 0.3335 | 0.4763 |
|
54 |
+
| 0.1698 | 0.89 | 1000 | 0.2487 | 0.4052 | 0.5660 |
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|