Training in progress epoch 0
Browse files- README.md +3 -3
- config.json +1 -1
- tf_model.h5 +1 -1
README.md
CHANGED
@@ -15,8 +15,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Train Loss:
|
19 |
-
- Validation Loss:
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
-
|
|
47 |
|
48 |
|
49 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 1.8220
|
19 |
+
- Validation Loss: 1.5969
|
20 |
- Epoch: 0
|
21 |
|
22 |
## Model description
|
|
|
43 |
|
44 |
| Train Loss | Validation Loss | Epoch |
|
45 |
|:----------:|:---------------:|:-----:|
|
46 |
+
| 1.8220 | 1.5969 | 0 |
|
47 |
|
48 |
|
49 |
### Framework versions
|
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_name_or_path": "xlm-roberta-base",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
1 |
{
|
2 |
"_name_or_path": "xlm-roberta-base",
|
3 |
"architectures": [
|
4 |
+
"XLMRobertaForMaskedLM"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1883070616
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c634ead96ec6508274323aac67ac039394f606df502e2139ec5386000ae89ad0
|
3 |
size 1883070616
|