WillLoki/distilbert-base-uncased-lora-text-classification
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
- Accuracy: {'accuracy': 0.885}
|
| 23 |
|
| 24 |
## Model description
|
|
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
|
| 53 |
-
| No log | 1.0 | 250 | 0.
|
| 54 |
-
| 0.
|
| 55 |
-
| 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4675
|
| 22 |
- Accuracy: {'accuracy': 0.885}
|
| 23 |
|
| 24 |
## Model description
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|:-------------------:|
|
| 53 |
+
| No log | 1.0 | 250 | 0.5274 | {'accuracy': 0.874} |
|
| 54 |
+
| 0.2336 | 2.0 | 500 | 0.4621 | {'accuracy': 0.873} |
|
| 55 |
+
| 0.2336 | 3.0 | 750 | 0.5047 | {'accuracy': 0.874} |
|
| 56 |
+
| 0.2293 | 4.0 | 1000 | 0.4725 | {'accuracy': 0.884} |
|
| 57 |
+
| 0.2293 | 5.0 | 1250 | 0.4214 | {'accuracy': 0.881} |
|
| 58 |
+
| 0.2034 | 6.0 | 1500 | 0.4845 | {'accuracy': 0.866} |
|
| 59 |
+
| 0.2034 | 7.0 | 1750 | 0.4923 | {'accuracy': 0.875} |
|
| 60 |
+
| 0.1519 | 8.0 | 2000 | 0.4627 | {'accuracy': 0.886} |
|
| 61 |
+
| 0.1519 | 9.0 | 2250 | 0.4626 | {'accuracy': 0.888} |
|
| 62 |
+
| 0.1232 | 10.0 | 2500 | 0.4675 | {'accuracy': 0.885} |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
runs/Feb21_16-16-16_cde6f636587a/events.out.tfevents.1740154577.cde6f636587a.2156.12
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98b12d26ede56d767f80cf55e2caa9497c3832f3f61f05feab3fd30c6878b9de
|
| 3 |
+
size 9274
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31235710e183ee1c62881989503809c68d9bf825e9d861666ff780b14c9e2055
|
| 3 |
size 5432
|