End of training
Browse files
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 1.
|
| 22 |
- Accuracy: 0.5725
|
| 23 |
|
| 24 |
## Model description
|
|
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
-
| No log | 1.0 | 79 | 1.
|
| 55 |
-
| No log | 2.0 | 158 | 1.
|
| 56 |
-
| No log | 3.0 | 237 | 1.
|
| 57 |
-
| No log | 4.0 | 316 | 1.
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.5297
|
| 22 |
- Accuracy: 0.5725
|
| 23 |
|
| 24 |
## Model description
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 54 |
+
| No log | 1.0 | 79 | 1.8352 | 0.5390 |
|
| 55 |
+
| No log | 2.0 | 158 | 1.6333 | 0.5242 |
|
| 56 |
+
| No log | 3.0 | 237 | 1.5604 | 0.5428 |
|
| 57 |
+
| No log | 4.0 | 316 | 1.5297 | 0.5725 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
runs/Nov25_13-03-31_tsf-508-wpa-1-223.epfl.ch/events.out.tfevents.1764072213.tsf-508-wpa-1-223.epfl.ch.7606.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef14d5110f99b83c1852a6ac1d800fb661963085e1996da0c4141a617d7e92c0
|
| 3 |
+
size 7068
|