update model card README.md
Browse files
README.md
CHANGED
@@ -12,9 +12,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# distilroberta-base-wiki-mark
|
14 |
|
15 |
-
This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
-
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,22 +44,11 @@ The following hyperparameters were used during training:
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
-
- num_epochs:
|
43 |
-
|
44 |
-
### Training results
|
45 |
-
|
46 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
-
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
-
| 2.2545 | 1.0 | 2028 | 2.3260 |
|
49 |
-
| 2.2803 | 2.0 | 4056 | 2.2899 |
|
50 |
-
| 2.24 | 3.0 | 6084 | 2.1889 |
|
51 |
-
| 2.2414 | 4.0 | 8112 | 2.2387 |
|
52 |
-
| 2.1412 | 5.0 | 10140 | 2.1748 |
|
53 |
-
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
-
- Pytorch 1.
|
59 |
- Datasets 2.3.2
|
60 |
- Tokenizers 0.12.1
|
|
|
12 |
|
13 |
# distilroberta-base-wiki-mark
|
14 |
|
15 |
+
This model is a fine-tuned version of [yochen/distilroberta-base-wiki-mark](https://huggingface.co/yochen/distilroberta-base-wiki-mark) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- eval_loss: 2.2695
|
18 |
+
- eval_runtime: 4.3489
|
19 |
+
- eval_samples_per_second: 431.836
|
20 |
+
- eval_steps_per_second: 54.037
|
21 |
+
- epoch: 10.1
|
22 |
+
- step: 20489
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
44 |
- seed: 42
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
|
49 |
### Framework versions
|
50 |
|
51 |
+
- Transformers 4.20.1
|
52 |
+
- Pytorch 1.12.0+cu102
|
53 |
- Datasets 2.3.2
|
54 |
- Tokenizers 0.12.1
|