FabianWillner
commited on
Commit
路
b015557
1
Parent(s):
259e81d
update model card README.md
Browse files
README.md
CHANGED
@@ -12,9 +12,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
12 |
|
13 |
# distilbert-base-uncased-finetuned-triviaqa
|
14 |
|
15 |
-
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Loss: 0.
|
18 |
|
19 |
## Model description
|
20 |
|
@@ -39,18 +39,19 @@ 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 |
-
|
|
|
|
49 |
|
50 |
|
51 |
### Framework versions
|
52 |
|
53 |
-
- Transformers 4.
|
54 |
- Pytorch 1.11.0+cu113
|
55 |
-
- Datasets 2.
|
56 |
- Tokenizers 0.12.1
|
|
|
12 |
|
13 |
# distilbert-base-uncased-finetuned-triviaqa
|
14 |
|
15 |
+
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.9949
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
39 |
- seed: 42
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
+
- num_epochs: 2
|
43 |
|
44 |
### Training results
|
45 |
|
46 |
| Training Loss | Epoch | Step | Validation Loss |
|
47 |
|:-------------:|:-----:|:-----:|:---------------:|
|
48 |
+
| 1.0391 | 1.0 | 11195 | 1.0133 |
|
49 |
+
| 0.8425 | 2.0 | 22390 | 0.9949 |
|
50 |
|
51 |
|
52 |
### Framework versions
|
53 |
|
54 |
+
- Transformers 4.19.2
|
55 |
- Pytorch 1.11.0+cu113
|
56 |
+
- Datasets 2.2.2
|
57 |
- Tokenizers 0.12.1
|